github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14509] qwen3.5:35b-a3b cannot be used under Vulkan #55926

New Issue
Closed
opened 2026-04-29 09:57:38 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 09:57:38 -05:00
Owner
Copy Link

Originally created by @junzhang-bjtu on GitHub (Feb 28, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14509

What is the issue?

qwen3.5:35b-a3b cannot be used under Vulkan.

Memory usage was unnormal as well. It is too high.

Error message: 500 Internal Server Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details.

Qwen3.5-Plus says: On Windows, the Ollama runner process crashes with an EXCEPTION_ACCESS_VIOLATION (0xc0000005) during inference when handling a POST /api/generate request, specifically within the CGO call to ggml_backend_sched_graph_compute_async in the GGML backend; this causes the runner to terminate unexpectedly and results in a wsarecv: An existing connection was forcibly closed by the remote host error on the server side. The crash occurs during computeBatch execution, suggesting a potential memory access issue in the native GGML/llama.cpp code, possibly triggered by GPU backend interactions (CUDA/Vulkan), model compatibility, or resource constraints—stack trace and full logs are available for debugging.

Other information:

  • OS: Windows 11 IoT Enterprise LTSC
  • CPU: Intel(R) Core(TM) Ultra 9 285H
  • GPU: Intel(R) Arc(TM) 140T GPU (48GB)
  • RAM: 96GB

Relevant log output

time=2026-02-28T16:14:39.249+08:00 level=INFO source=routes.go:1663 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:0 OLLAMA_DEBUG:INFO OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\Jun\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES:]"
time=2026-02-28T16:14:39.253+08:00 level=INFO source=routes.go:1665 msg="Ollama cloud disabled: false"
time=2026-02-28T16:14:39.255+08:00 level=INFO source=images.go:473 msg="total blobs: 11"
time=2026-02-28T16:14:39.255+08:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0"
time=2026-02-28T16:14:39.256+08:00 level=INFO source=routes.go:1718 msg="Listening on 127.0.0.1:11434 (version 0.17.4)"
time=2026-02-28T16:14:39.257+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-02-28T16:14:39.271+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62321"
time=2026-02-28T16:14:46.169+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50177"
time=2026-02-28T16:14:48.380+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50187"
time=2026-02-28T16:15:00.083+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50215"
time=2026-02-28T16:15:07.280+08:00 level=INFO source=types.go:42 msg="inference compute" id=8680517d-0300-0000-0002-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="Intel(R) Arc(TM) 140T GPU (48GB)" libdirs=ollama,vulkan driver=0.0 pci_id="" type=iGPU total="54.5 GiB" available="52.6 GiB"
time=2026-02-28T16:15:07.280+08:00 level=INFO source=routes.go:1768 msg="vram-based default context" total_vram="54.5 GiB" default_num_ctx=262144
[GIN] 2026/02/28 - 16:15:07 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/02/28 - 16:15:07 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/02/28 - 16:15:07 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/02/28 - 16:15:07 | 200 |     22.2806ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:15:07 | 200 |    135.5835ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/02/28 - 16:15:07 | 200 |    468.8457ms |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/02/28 - 16:15:07 | 200 |    473.7447ms |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/02/28 - 16:15:38 | 200 |      1.5901ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:16:09 | 200 |      3.6354ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:16:40 | 200 |      3.8152ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:17:11 | 200 |      5.5377ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:17:42 | 200 |      2.9467ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:17:54 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/02/28 - 16:17:54 | 200 |      1.0638ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:18:03 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2026/02/28 - 16:18:03 | 200 |      2.1408ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:18:10 | 200 |       545.7µs |       127.0.0.1 | HEAD     "/"
[GIN] 2026/02/28 - 16:18:10 | 200 |     99.7245ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/02/28 - 16:18:10 | 200 |      3.8039ms |       127.0.0.1 | POST     "/api/generate"
[GIN] 2026/02/28 - 16:18:10 | 200 |     12.9691ms |       127.0.0.1 | DELETE   "/api/delete"
[GIN] 2026/02/28 - 16:18:17 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2026/02/28 - 16:18:17 | 200 |     69.1778ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/02/28 - 16:18:17 | 200 |      1.6694ms |       127.0.0.1 | POST     "/api/generate"
[GIN] 2026/02/28 - 16:18:17 | 200 |    118.1322ms |       127.0.0.1 | DELETE   "/api/delete"
[GIN] 2026/02/28 - 16:18:24 | 200 |      2.5591ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:18:30 | 200 |            0s |       127.0.0.1 | HEAD     "/"
time=2026-02-28T16:18:32.328+08:00 level=INFO source=download.go:179 msg="downloading 2abd0d805943 in 24 1 GB part(s)"
[GIN] 2026/02/28 - 16:18:54 | 200 |      1.8981ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:19:24 | 200 |      1.6113ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:19:54 | 200 |      1.6017ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:20:24 | 200 |      1.6557ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:20:54 | 200 |      2.1882ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:21:24 | 200 |      1.7017ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:21:54 | 200 |     16.9456ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:22:24 | 200 |      2.4098ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:22:54 | 200 |      1.6473ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:23:24 | 200 |      1.8695ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:23:54 | 200 |      1.5804ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:24:24 | 200 |      2.8267ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:24:54 | 200 |      1.6257ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:25:24 | 200 |      1.6215ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:25:54 | 200 |      1.1228ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:26:24 | 200 |      2.3629ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:26:54 | 200 |      2.1945ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:27:24 | 200 |       1.156ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:27:54 | 200 |      2.1764ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:28:24 | 200 |      2.4375ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:28:54 | 200 |      1.4537ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:29:24 | 200 |      1.6271ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:29:54 | 200 |      1.6367ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:30:25 | 200 |      2.5413ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:30:56 | 200 |      2.2542ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:31:21 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/02/28 - 16:31:21 | 200 |      1.6514ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:31:22 | 200 |    850.9832ms |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/02/28 - 16:31:52 | 200 |      1.6015ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:32:23 | 200 |      2.1386ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:32:54 | 200 |       544.4µs |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:33:25 | 200 |      1.6493ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:33:56 | 200 |      1.8344ms |       127.0.0.1 | GET      "/api/tags"
time=2026-02-28T16:34:04.350+08:00 level=INFO source=download.go:179 msg="downloading 7339fa418c9a in 1 11 KB part(s)"
time=2026-02-28T16:34:05.998+08:00 level=INFO source=download.go:179 msg="downloading f6417cb1e269 in 1 42 B part(s)"
time=2026-02-28T16:34:07.657+08:00 level=INFO source=download.go:179 msg="downloading 9850298a701d in 1 482 B part(s)"
[GIN] 2026/02/28 - 16:34:27 | 200 |            0s |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:34:29 | 200 |        15m58s |       127.0.0.1 | POST     "/api/pull"
[GIN] 2026/02/28 - 16:34:58 | 200 |      2.3193ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:35:29 | 200 |      1.8509ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:36:00 | 200 |      3.5136ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:36:31 | 200 |      3.4253ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:36:43 | 200 |       527.6µs |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/02/28 - 16:36:43 | 200 |      1.0614ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:36:43 | 200 |    437.1146ms |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/02/28 - 16:36:46 | 200 |      1.0373ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:36:46 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/02/28 - 16:36:46 | 404 |       512.7µs |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/02/28 - 16:36:46 | 200 |    337.8204ms |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/02/28 - 16:36:46 | 200 |    310.6224ms |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/02/28 - 16:36:50 | 200 |    119.8769ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/02/28 - 16:37:16 | 200 |      1.0308ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:37:17 | 200 |      1.0514ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/02/28 - 16:37:18 | 200 |    119.4887ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/02/28 - 16:37:18 | 200 |    119.5315ms |       127.0.0.1 | POST     "/api/show"
time=2026-02-28T16:37:18.316+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 49788"
time=2026-02-28T16:37:19.273+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-02-28T16:37:19.273+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2026-02-28T16:37:19.273+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=16 efficiency=10 threads=16
time=2026-02-28T16:37:19.353+08:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-02-28T16:37:19.354+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\Jun\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 49828"
time=2026-02-28T16:37:19.361+08:00 level=INFO source=sched.go:491 msg="system memory" total="95.4 GiB" free="79.6 GiB" free_swap="85.0 GiB"
time=2026-02-28T16:37:19.361+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=8680517d-0300-0000-0002-000000000000 library=Vulkan available="52.0 GiB" free="52.5 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-02-28T16:37:19.361+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1
time=2026-02-28T16:37:19.401+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
time=2026-02-28T16:37:19.404+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:49828"
time=2026-02-28T16:37:19.405+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:262144 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-28T16:37:19.442+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35moe file_type=Q4_K_M name="" description="" num_tensors=1959 num_key_values=57
load_backend: loaded CPU backend from C:\Users\Jun\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Intel(R) Arc(TM) 140T GPU (48GB) (Intel Corporation) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none
load_backend: loaded Vulkan backend from C:\Users\Jun\AppData\Local\Programs\Ollama\lib\ollama\vulkan\ggml-vulkan.dll
time=2026-02-28T16:37:19.520+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000
ggml_backend_vk_get_device_memory called: luid 0x0000000000010874
ggml_dxgi_pdh_init called
DXGI + PDH Initialized. Getting GPU free memory info
[DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (48GB), LUID: 0x0000000000010874, Dedicated: 0.12 GB, Shared: 54.40 GB
[DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000010CBE, Dedicated: 0.00 GB, Shared: 54.40 GB
Integrated GPU (Intel(R) Arc(TM) 140T GPU (48GB)) with LUID 0x0000000000010874 detected. Shared Total: 58409310535.00 bytes (54.40 GB), Shared Usage: 2203336704.00 bytes (2.05 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB)
ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 56340191559 total: 58543528263
time=2026-02-28T16:37:21.213+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:262144 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000
ggml_backend_vk_get_device_memory called: luid 0x0000000000010874
ggml_dxgi_pdh_init called
DXGI + PDH Initialized. Getting GPU free memory info
[DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (48GB), LUID: 0x0000000000010874, Dedicated: 0.12 GB, Shared: 54.40 GB
[DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000010CBE, Dedicated: 0.00 GB, Shared: 54.40 GB
Integrated GPU (Intel(R) Arc(TM) 140T GPU (48GB)) with LUID 0x0000000000010874 detected. Shared Total: 58409310535.00 bytes (54.40 GB), Shared Usage: 2204721152.00 bytes (2.05 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB)
ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 56338807111 total: 58543528263
time=2026-02-28T16:37:26.388+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:262144 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="21.9 GiB"
time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="277.3 MiB"
time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="6.5 GiB"
time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="3.4 GiB"
time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="33.0 MiB"
time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:272 msg="total memory" size="32.2 GiB"
time=2026-02-28T16:37:26.388+08:00 level=INFO source=ggml.go:482 msg="offloading 40 repeating layers to GPU"
time=2026-02-28T16:37:26.388+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1
time=2026-02-28T16:37:26.388+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-02-28T16:37:26.388+08:00 level=INFO source=ggml.go:494 msg="offloaded 41/41 layers to GPU"
time=2026-02-28T16:37:26.388+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
time=2026-02-28T16:37:26.389+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model"
[GIN] 2026/02/28 - 16:37:48 | 200 |      1.6013ms |       127.0.0.1 | GET      "/api/tags"
time=2026-02-28T16:37:59.687+08:00 level=INFO source=server.go:1388 msg="llama runner started in 40.33 seconds"
Exception 0xc0000005 0x1 0x22e1000 0x7ffb84a5be7b
PC=0x7ffb84a5be7b
signal arrived during external code execution

runtime.cgocall(0x7ff7ef467560, 0xc00299daa0)
	runtime/cgocall.go:167 +0x3e fp=0xc00299da78 sp=0xc00299da10 pc=0x7ff7ee58243e
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x1b1fad2d5c0, 0x1b24a88ac20)
	_cgo_gotypes.go:963 +0x50 fp=0xc00299daa0 sp=0xc00299da78 pc=0x7ff7eea85310
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func2(...)
	github.com/ollama/ollama/ml/backend/ggml/ggml.go:825
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify(0xc000a6a9c0, 0xc0029fadc0?, {0xc001a29a90, 0x1, 0x2?})
	github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 +0x1b5 fp=0xc00299db78 sp=0xc00299daa0 pc=0x7ff7eea94bd5
github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc00055a780, {0x0, {0x7ff7efd036e0, 0xc000a6a9c0}, {0x7ff7efd134c8, 0xc0035d6348}, {0xc0029f5208, 0xa7, 0x11f}, {{0x7ff7efd134c8, ...}, ...}, ...})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:716 +0x862 fp=0xc00299def0 sp=0xc00299db78 pc=0x7ff7eebbfa82
github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1()
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc00299dfe0 sp=0xc00299def0 pc=0x7ff7eebbd778
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00299dfe8 sp=0xc00299dfe0 pc=0x7ff7ee58d9a1
created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 13
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd

goroutine 1 gp=0xc0000021c0 m=nil [IO wait]:
runtime.gopark(0x7ff7ee58f1a0?, 0x7ff7f07b92e0?, 0x20?, 0xd4?, 0xc00047d4cc?)
	runtime/proc.go:435 +0xce fp=0xc000383630 sp=0xc000383610 pc=0x7ff7ee58598e
runtime.netpollblock(0x274?, 0xee520406?, 0xf7?)
	runtime/netpoll.go:575 +0xf7 fp=0xc000383668 sp=0xc000383630 pc=0x7ff7ee54bdf7
internal/poll.runtime_pollWait(0x1b1f3e8c970, 0x72)
	runtime/netpoll.go:351 +0x85 fp=0xc000383688 sp=0xc000383668 pc=0x7ff7ee584b25
internal/poll.(*pollDesc).wait(0x7ff7ee61a953?, 0x0?, 0x0)
	internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0003836b0 sp=0xc000383688 pc=0x7ff7ee61bf47
internal/poll.execIO(0xc00047d420, 0xc00058f758)
	internal/poll/fd_windows.go:177 +0x105 fp=0xc000383728 sp=0xc0003836b0 pc=0x7ff7ee61d3a5
internal/poll.(*FD).acceptOne(0xc00047d408, 0x280, {0xc00015e0f0?, 0xc00058f7b8?, 0x7ff7ee625065?}, 0xc00058f7ec?)
	internal/poll/fd_windows.go:946 +0x65 fp=0xc000383788 sp=0xc000383728 pc=0x7ff7ee621925
internal/poll.(*FD).Accept(0xc00047d408, 0xc000383938)
	internal/poll/fd_windows.go:980 +0x1b6 fp=0xc000383840 sp=0xc000383788 pc=0x7ff7ee621c56
net.(*netFD).accept(0xc00047d408)
	net/fd_windows.go:182 +0x4b fp=0xc000383958 sp=0xc000383840 pc=0x7ff7ee69358b
net.(*TCPListener).accept(0xc00051ee00)
	net/tcpsock_posix.go:159 +0x1b fp=0xc0003839a8 sp=0xc000383958 pc=0x7ff7ee6a9b3b
net.(*TCPListener).Accept(0xc00051ee00)
	net/tcpsock.go:380 +0x30 fp=0xc0003839d8 sp=0xc0003839a8 pc=0x7ff7ee6a88f0
net/http.(*onceCloseListener).Accept(0xc000142480?)
	<autogenerated>:1 +0x24 fp=0xc0003839f0 sp=0xc0003839d8 pc=0x7ff7ee8c1fe4
net/http.(*Server).Serve(0xc0001cfa00, {0x7ff7efcf4710, 0xc00051ee00})
	net/http/server.go:3424 +0x30c fp=0xc000383b20 sp=0xc0003839f0 pc=0x7ff7ee8998ac
github.com/ollama/ollama/runner/ollamarunner.Execute({0xc00004e0b0, 0x4, 0x5})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:1447 +0x94e fp=0xc000383cf0 sp=0xc000383b20 pc=0x7ff7eebc6a2e
github.com/ollama/ollama/runner.Execute({0xc00004e090?, 0x0?, 0x0?})
	github.com/ollama/ollama/runner/runner.go:18 +0x12b fp=0xc000383d30 sp=0xc000383cf0 pc=0x7ff7eebd184b
github.com/ollama/ollama/cmd.NewCLI.func3(0xc0001cf600?, {0x7ff7efacd112?, 0x4?, 0x7ff7efacd116?})
	github.com/ollama/ollama/cmd/cmd.go:2270 +0x45 fp=0xc000383d58 sp=0xc000383d30 pc=0x7ff7ef3f84e5
github.com/spf13/cobra.(*Command).execute(0xc000145b08, {0xc0000e1ea0, 0x5, 0x5})
	github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000383e78 sp=0xc000383d58 pc=0x7ff7ee70e75c
github.com/spf13/cobra.(*Command).ExecuteC(0xc000552f08)
	github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000383f30 sp=0xc000383e78 pc=0x7ff7ee70efa5
github.com/spf13/cobra.(*Command).Execute(...)
	github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
	github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
	github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000383f50 sp=0xc000383f30 pc=0x7ff7ef3fa98d
runtime.main()
	runtime/proc.go:283 +0x27d fp=0xc000383fe0 sp=0xc000383f50 pc=0x7ff7ee554ddd
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000383fe8 sp=0xc000383fe0 pc=0x7ff7ee58d9a1

goroutine 2 gp=0xc0000028c0 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000081fa8 sp=0xc000081f88 pc=0x7ff7ee58598e
runtime.goparkunlock(...)
	runtime/proc.go:441
runtime.forcegchelper()
	runtime/proc.go:348 +0xb8 fp=0xc000081fe0 sp=0xc000081fa8 pc=0x7ff7ee5550f8
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff7ee58d9a1
created by runtime.init.7 in goroutine 1
	runtime/proc.go:336 +0x1a

goroutine 3 gp=0xc000002c40 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000083f80 sp=0xc000083f60 pc=0x7ff7ee58598e
runtime.goparkunlock(...)
	runtime/proc.go:441
runtime.bgsweep(0xc00008a000)
	runtime/mgcsweep.go:316 +0xdf fp=0xc000083fc8 sp=0xc000083f80 pc=0x7ff7ee53debf
runtime.gcenable.gowrap1()
	runtime/mgc.go:204 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff7ee532285
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff7ee58d9a1
created by runtime.gcenable in goroutine 1
	runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000002e00 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x42c1d800?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000091f78 sp=0xc000091f58 pc=0x7ff7ee58598e
runtime.goparkunlock(...)
	runtime/proc.go:441
runtime.(*scavengerState).park(0x7ff7f07e3080)
	runtime/mgcscavenge.go:425 +0x49 fp=0xc000091fa8 sp=0xc000091f78 pc=0x7ff7ee53b909
runtime.bgscavenge(0xc00008a000)
	runtime/mgcscavenge.go:658 +0x59 fp=0xc000091fc8 sp=0xc000091fa8 pc=0x7ff7ee53be99
runtime.gcenable.gowrap2()
	runtime/mgc.go:205 +0x25 fp=0xc000091fe0 sp=0xc000091fc8 pc=0x7ff7ee532225
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000091fe8 sp=0xc000091fe0 pc=0x7ff7ee58d9a1
created by runtime.gcenable in goroutine 1
	runtime/mgc.go:205 +0xa5

goroutine 5 gp=0xc000003340 m=nil [finalizer wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000093e30 sp=0xc000093e10 pc=0x7ff7ee58598e
runtime.runfinq()
	runtime/mfinal.go:196 +0x107 fp=0xc000093fe0 sp=0xc000093e30 pc=0x7ff7ee531207
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000093fe8 sp=0xc000093fe0 pc=0x7ff7ee58d9a1
created by runtime.createfing in goroutine 1
	runtime/mfinal.go:166 +0x3d

goroutine 6 gp=0xc000003dc0 m=nil [chan receive]:
runtime.gopark(0xc0002014a0?, 0xc118080000?, 0x60?, 0x5f?, 0x7ff7ee67c1a8?)
	runtime/proc.go:435 +0xce fp=0xc000085f18 sp=0xc000085ef8 pc=0x7ff7ee58598e
runtime.chanrecv(0xc0000983f0, 0x0, 0x1)
	runtime/chan.go:664 +0x445 fp=0xc000085f90 sp=0xc000085f18 pc=0x7ff7ee522d45
runtime.chanrecv1(0x7ff7ee554f40?, 0xc000085f76?)
	runtime/chan.go:506 +0x12 fp=0xc000085fb8 sp=0xc000085f90 pc=0x7ff7ee5228d2
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
	runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
	runtime/mgc.go:1799 +0x2f fp=0xc000085fe0 sp=0xc000085fb8 pc=0x7ff7ee5354af
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff7ee58d9a1
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
	runtime/mgc.go:1794 +0x85

goroutine 7 gp=0xc0003f8380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00008df38 sp=0xc00008df18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc00008dfc8 sp=0xc00008df38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00008dfe0 sp=0xc00008dfc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00008dfe8 sp=0xc00008dfe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 18 gp=0xc0001061c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000113f38 sp=0xc000113f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc000113fc8 sp=0xc000113f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000113fe0 sp=0xc000113fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000113fe8 sp=0xc000113fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 34 gp=0xc000484000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00010ff38 sp=0xc00010ff18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc00010ffc8 sp=0xc00010ff38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00010ffe0 sp=0xc00010ffc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00010ffe8 sp=0xc00010ffe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 35 gp=0xc0004841c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000111f38 sp=0xc000111f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc000111fc8 sp=0xc000111f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000111fe0 sp=0xc000111fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000111fe8 sp=0xc000111fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 8 gp=0xc0003f8540 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00008ff38 sp=0xc00008ff18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc00008ffc8 sp=0xc00008ff38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00008ffe0 sp=0xc00008ffc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00008ffe8 sp=0xc00008ffe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 9 gp=0xc0003f8700 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000473f38 sp=0xc000473f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc000473fc8 sp=0xc000473f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000473fe0 sp=0xc000473fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000473fe8 sp=0xc000473fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 10 gp=0xc0003f88c0 m=nil [GC worker (idle)]:
runtime.gopark(0x179d1a147c9c4?, 0x3?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000475f38 sp=0xc000475f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc000475fc8 sp=0xc000475f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000475fe0 sp=0xc000475fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000475fe8 sp=0xc000475fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 11 gp=0xc0003f8a80 m=nil [GC worker (idle)]:
runtime.gopark(0x179d0cb9c1334?, 0x3?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00046ff38 sp=0xc00046ff18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc00046ffc8 sp=0xc00046ff38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00046ffe0 sp=0xc00046ffc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00046ffe8 sp=0xc00046ffe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 19 gp=0xc000106380 m=nil [GC worker (idle)]:
runtime.gopark(0x179d1a1501c3c?, 0x1?, 0x5c?, 0x26?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000115f38 sp=0xc000115f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc000115fc8 sp=0xc000115f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000115fe0 sp=0xc000115fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000115fe8 sp=0xc000115fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 12 gp=0xc0003f8c40 m=nil [GC worker (idle)]:
runtime.gopark(0x179d1a13deb98?, 0x3?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000471f38 sp=0xc000471f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc000471fc8 sp=0xc000471f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000471fe0 sp=0xc000471fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000471fe8 sp=0xc000471fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 36 gp=0xc000484540 m=nil [GC worker (idle)]:
runtime.gopark(0x179d1a1501c3c?, 0x1?, 0xa8?, 0x31?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000491f38 sp=0xc000491f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc000491fc8 sp=0xc000491f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000491fe0 sp=0xc000491fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000491fe8 sp=0xc000491fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 37 gp=0xc000484700 m=nil [GC worker (idle)]:
runtime.gopark(0x179d0cb9c1334?, 0x1?, 0x48?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000493f38 sp=0xc000493f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc000493fc8 sp=0xc000493f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000493fe0 sp=0xc000493fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000493fe8 sp=0xc000493fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 38 gp=0xc0004848c0 m=nil [GC worker (idle)]:
runtime.gopark(0x179d1a13deb98?, 0x3?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 39 gp=0xc000484a80 m=nil [GC worker (idle)]:
runtime.gopark(0x179d1a13deb98?, 0x3?, 0xd0?, 0xba?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00048ff38 sp=0xc00048ff18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc00048ffc8 sp=0xc00048ff38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00048ffe0 sp=0xc00048ffc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00048ffe8 sp=0xc00048ffe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 40 gp=0xc000484c40 m=nil [GC worker (idle)]:
runtime.gopark(0x179d1a147c9c4?, 0x1?, 0x98?, 0x88?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000499f38 sp=0xc000499f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc000499fc8 sp=0xc000499f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000499fe0 sp=0xc000499fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000499fe8 sp=0xc000499fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 41 gp=0xc000484e00 m=nil [GC worker (idle)]:
runtime.gopark(0x179d0cb9c1334?, 0x3?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00049bf38 sp=0xc00049bf18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099810)
	runtime/mgc.go:1423 +0xe9 fp=0xc00049bfc8 sp=0xc00049bf38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00049bfe0 sp=0xc00049bfc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00049bfe8 sp=0xc00049bfe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 13 gp=0xc000106a80 m=nil [chan receive]:
runtime.gopark(0x30?, 0x7ff7efa26ba0?, 0x1?, 0x0?, 0xc0004a3798?)
	runtime/proc.go:435 +0xce fp=0xc0004a3750 sp=0xc0004a3730 pc=0x7ff7ee58598e
runtime.chanrecv(0xc000c14310, 0x0, 0x1)
	runtime/chan.go:664 +0x445 fp=0xc0004a37c8 sp=0xc0004a3750 pc=0x7ff7ee522d45
runtime.chanrecv1(0x7ff7efb118ca?, 0x29?)
	runtime/chan.go:506 +0x12 fp=0xc0004a37f0 sp=0xc0004a37c8 pc=0x7ff7ee5228d2
github.com/ollama/ollama/runner/ollamarunner.(*Server).forwardBatch(_, {0x1, {0x7ff7efd036e0, 0xc00334a480}, {0x7ff7efd134c8, 0xc003604cf0}, {0xc00333a4d8, 0x1, 0x1}, {{0x7ff7efd134c8, ...}, ...}, ...})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:476 +0xfa fp=0xc0004a3b58 sp=0xc0004a37f0 pc=0x7ff7eebbd89a
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc00055a780, {0x7ff7efcf7030, 0xc00015c000})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:453 +0x18c fp=0xc0004a3fb8 sp=0xc0004a3b58 pc=0x7ff7eebbd54c
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
	github.com/ollama/ollama/runner/ollamarunner/runner.go:1424 +0x28 fp=0xc0004a3fe0 sp=0xc0004a3fb8 pc=0x7ff7eebc6ca8
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a3fe8 sp=0xc0004a3fe0 pc=0x7ff7ee58d9a1
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
	github.com/ollama/ollama/runner/ollamarunner/runner.go:1424 +0x4c9

goroutine 14 gp=0xc000106c40 m=nil [select]:
runtime.gopark(0xc000047a08?, 0x2?, 0xc0?, 0x77?, 0xc00004786c?)
	runtime/proc.go:435 +0xce fp=0xc000047698 sp=0xc000047678 pc=0x7ff7ee58598e
runtime.selectgo(0xc000047a08, 0xc000047868, 0xa7?, 0x0, 0x1?, 0x1)
	runtime/select.go:351 +0x837 fp=0xc0000477d0 sp=0xc000047698 pc=0x7ff7ee566437
github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc00055a780, {0x7ff7efcf48c0, 0xc000b58fc0}, 0xc000b60f00)
	github.com/ollama/ollama/runner/ollamarunner/runner.go:956 +0xc4e fp=0xc000047ac0 sp=0xc0000477d0 pc=0x7ff7eebc1d2e
github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x7ff7efcf48c0?, 0xc000b58fc0?}, 0xc000047b40?)
	<autogenerated>:1 +0x36 fp=0xc000047af0 sp=0xc000047ac0 pc=0x7ff7eebc7196
net/http.HandlerFunc.ServeHTTP(0xc00053c3c0?, {0x7ff7efcf48c0?, 0xc000b58fc0?}, 0xc000047b60?)
	net/http/server.go:2294 +0x29 fp=0xc000047b18 sp=0xc000047af0 pc=0x7ff7ee895ee9
net/http.(*ServeMux).ServeHTTP(0x7ff7ee52b785?, {0x7ff7efcf48c0, 0xc000b58fc0}, 0xc000b60f00)
	net/http/server.go:2822 +0x1c4 fp=0xc000047b68 sp=0xc000047b18 pc=0x7ff7ee897de4
net/http.serverHandler.ServeHTTP({0x7ff7efcf0af0?}, {0x7ff7efcf48c0?, 0xc000b58fc0?}, 0x1?)
	net/http/server.go:3301 +0x8e fp=0xc000047b98 sp=0xc000047b68 pc=0x7ff7ee8b586e
net/http.(*conn).serve(0xc000142480, {0x7ff7efcf6ff8, 0xc000257590})
	net/http/server.go:2102 +0x625 fp=0xc000047fb8 sp=0xc000047b98 pc=0x7ff7ee8943e5
net/http.(*Server).Serve.gowrap3()
	net/http/server.go:3454 +0x28 fp=0xc000047fe0 sp=0xc000047fb8 pc=0x7ff7ee899ca8
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000047fe8 sp=0xc000047fe0 pc=0x7ff7ee58d9a1
created by net/http.(*Server).Serve in goroutine 1
	net/http/server.go:3454 +0x485

goroutine 2183 gp=0xc000106fc0 m=nil [IO wait]:
runtime.gopark(0x0?, 0xc00047d6a0?, 0x48?, 0xd7?, 0xc00047d74c?)
	runtime/proc.go:435 +0xce fp=0xc0004b5d58 sp=0xc0004b5d38 pc=0x7ff7ee58598e
runtime.netpollblock(0x27c?, 0xee520406?, 0xf7?)
	runtime/netpoll.go:575 +0xf7 fp=0xc0004b5d90 sp=0xc0004b5d58 pc=0x7ff7ee54bdf7
internal/poll.runtime_pollWait(0x1b1f3e8c858, 0x72)
	runtime/netpoll.go:351 +0x85 fp=0xc0004b5db0 sp=0xc0004b5d90 pc=0x7ff7ee584b25
internal/poll.(*pollDesc).wait(0x27c?, 0x72?, 0x0)
	internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0004b5dd8 sp=0xc0004b5db0 pc=0x7ff7ee61bf47
internal/poll.execIO(0xc00047d6a0, 0x7ff7efb51a00)
	internal/poll/fd_windows.go:177 +0x105 fp=0xc0004b5e50 sp=0xc0004b5dd8 pc=0x7ff7ee61d3a5
internal/poll.(*FD).Read(0xc00047d688, {0xc0003340a1, 0x1, 0x1})
	internal/poll/fd_windows.go:438 +0x29b fp=0xc0004b5ef0 sp=0xc0004b5e50 pc=0x7ff7ee61e07b
net.(*netFD).Read(0xc00047d688, {0xc0003340a1?, 0xc00059e0d8?, 0xc0004b5f70?})
	net/fd_posix.go:55 +0x25 fp=0xc0004b5f38 sp=0xc0004b5ef0 pc=0x7ff7ee691465
net.(*conn).Read(0xc00007a8e8, {0xc0003340a1?, 0xc0036270c0?, 0x7ff7ee914600?})
	net/net.go:194 +0x45 fp=0xc0004b5f80 sp=0xc0004b5f38 pc=0x7ff7ee6a0b85
net/http.(*connReader).backgroundRead(0xc000334090)
	net/http/server.go:690 +0x37 fp=0xc0004b5fc8 sp=0xc0004b5f80 pc=0x7ff7ee88e2b7
net/http.(*connReader).startBackgroundRead.gowrap2()
	net/http/server.go:686 +0x25 fp=0xc0004b5fe0 sp=0xc0004b5fc8 pc=0x7ff7ee88e1e5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b5fe8 sp=0xc0004b5fe0 pc=0x7ff7ee58d9a1
created by net/http.(*connReader).startBackgroundRead in goroutine 14
	net/http/server.go:686 +0xb6

goroutine 2238 gp=0xc000b24380 m=nil [chan receive]:
runtime.gopark(0x30?, 0x7ff7efa26ba0?, 0x1?, 0xbe?, 0xc000c1bb20?)
	runtime/proc.go:435 +0xce fp=0xc000c1bad8 sp=0xc000c1bab8 pc=0x7ff7ee58598e
runtime.chanrecv(0xc000a6e540, 0x0, 0x1)
	runtime/chan.go:664 +0x445 fp=0xc000c1bb50 sp=0xc000c1bad8 pc=0x7ff7ee522d45
runtime.chanrecv1(0x7ff7efb154d4?, 0x2c?)
	runtime/chan.go:506 +0x12 fp=0xc000c1bb78 sp=0xc000c1bb50 pc=0x7ff7ee5228d2
github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc00055a780, {0x1, {0x7ff7efd036e0, 0xc00334a480}, {0x7ff7efd134c8, 0xc003604cf0}, {0xc00333a4d8, 0x1, 0x1}, {{0x7ff7efd134c8, ...}, ...}, ...})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:645 +0x185 fp=0xc000c1bef0 sp=0xc000c1bb78 pc=0x7ff7eebbf3a5
github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1()
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc000c1bfe0 sp=0xc000c1bef0 pc=0x7ff7eebbd778
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000c1bfe8 sp=0xc000c1bfe0 pc=0x7ff7ee58d9a1
created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 13
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd
rax     0x0
rbx     0x0
rcx     0x1b7e051a0e0
rdx     0x0
rdi     0x80
rsi     0x22e1060
rbp     0x1b7e051a080
rsp     0x8f715ff330
r8      0x22e1000
r9      0x0
r10     0x22e1060
r11     0x0
r12     0x0
r13     0x1b24ab15730
r14     0x0
r15     0x0
rip     0x7ffb84a5be7b
rflags  0x10246
cs      0x33
fs      0x53
gs      0x2b
time=2026-02-28T16:38:04.508+08:00 level=ERROR source=server.go:1610 msg="post predict" error="Post \"http://127.0.0.1:49828/completion\": read tcp 127.0.0.1:49833->127.0.0.1:49828: wsarecv: An existing connection was forcibly closed by the remote host."

OS

Windows

GPU

Intel

CPU

Intel

Ollama version

0.17.4

Originally created by @junzhang-bjtu on GitHub (Feb 28, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14509 ### What is the issue? qwen3.5:35b-a3b cannot be used under Vulkan. Memory usage was unnormal as well. It is too high. > Error message: 500 Internal Server Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details. > **Qwen3.5-Plus says:** On Windows, the Ollama runner process crashes with an EXCEPTION_ACCESS_VIOLATION (0xc0000005) during inference when handling a POST /api/generate request, specifically within the CGO call to ggml_backend_sched_graph_compute_async in the GGML backend; this causes the runner to terminate unexpectedly and results in a wsarecv: An existing connection was forcibly closed by the remote host error on the server side. The crash occurs during computeBatch execution, suggesting a potential memory access issue in the native GGML/llama.cpp code, possibly triggered by GPU backend interactions (CUDA/Vulkan), model compatibility, or resource constraints—stack trace and full logs are available for debugging. Other information: - OS: Windows 11 IoT Enterprise LTSC - CPU: Intel(R) Core(TM) Ultra 9 285H - GPU: Intel(R) Arc(TM) 140T GPU (48GB) - RAM: 96GB ### Relevant log output ```shell time=2026-02-28T16:14:39.249+08:00 level=INFO source=routes.go:1663 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:0 OLLAMA_DEBUG:INFO OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\Jun\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES:]" time=2026-02-28T16:14:39.253+08:00 level=INFO source=routes.go:1665 msg="Ollama cloud disabled: false" time=2026-02-28T16:14:39.255+08:00 level=INFO source=images.go:473 msg="total blobs: 11" time=2026-02-28T16:14:39.255+08:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0" time=2026-02-28T16:14:39.256+08:00 level=INFO source=routes.go:1718 msg="Listening on 127.0.0.1:11434 (version 0.17.4)" time=2026-02-28T16:14:39.257+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2026-02-28T16:14:39.271+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62321" time=2026-02-28T16:14:46.169+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50177" time=2026-02-28T16:14:48.380+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50187" time=2026-02-28T16:15:00.083+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50215" time=2026-02-28T16:15:07.280+08:00 level=INFO source=types.go:42 msg="inference compute" id=8680517d-0300-0000-0002-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="Intel(R) Arc(TM) 140T GPU (48GB)" libdirs=ollama,vulkan driver=0.0 pci_id="" type=iGPU total="54.5 GiB" available="52.6 GiB" time=2026-02-28T16:15:07.280+08:00 level=INFO source=routes.go:1768 msg="vram-based default context" total_vram="54.5 GiB" default_num_ctx=262144 [GIN] 2026/02/28 - 16:15:07 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2026/02/28 - 16:15:07 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2026/02/28 - 16:15:07 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2026/02/28 - 16:15:07 | 200 | 22.2806ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:15:07 | 200 | 135.5835ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/02/28 - 16:15:07 | 200 | 468.8457ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/02/28 - 16:15:07 | 200 | 473.7447ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/02/28 - 16:15:38 | 200 | 1.5901ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:16:09 | 200 | 3.6354ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:16:40 | 200 | 3.8152ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:17:11 | 200 | 5.5377ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:17:42 | 200 | 2.9467ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:17:54 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2026/02/28 - 16:17:54 | 200 | 1.0638ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:18:03 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2026/02/28 - 16:18:03 | 200 | 2.1408ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:18:10 | 200 | 545.7µs | 127.0.0.1 | HEAD "/" [GIN] 2026/02/28 - 16:18:10 | 200 | 99.7245ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/02/28 - 16:18:10 | 200 | 3.8039ms | 127.0.0.1 | POST "/api/generate" [GIN] 2026/02/28 - 16:18:10 | 200 | 12.9691ms | 127.0.0.1 | DELETE "/api/delete" [GIN] 2026/02/28 - 16:18:17 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2026/02/28 - 16:18:17 | 200 | 69.1778ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/02/28 - 16:18:17 | 200 | 1.6694ms | 127.0.0.1 | POST "/api/generate" [GIN] 2026/02/28 - 16:18:17 | 200 | 118.1322ms | 127.0.0.1 | DELETE "/api/delete" [GIN] 2026/02/28 - 16:18:24 | 200 | 2.5591ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:18:30 | 200 | 0s | 127.0.0.1 | HEAD "/" time=2026-02-28T16:18:32.328+08:00 level=INFO source=download.go:179 msg="downloading 2abd0d805943 in 24 1 GB part(s)" [GIN] 2026/02/28 - 16:18:54 | 200 | 1.8981ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:19:24 | 200 | 1.6113ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:19:54 | 200 | 1.6017ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:20:24 | 200 | 1.6557ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:20:54 | 200 | 2.1882ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:21:24 | 200 | 1.7017ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:21:54 | 200 | 16.9456ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:22:24 | 200 | 2.4098ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:22:54 | 200 | 1.6473ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:23:24 | 200 | 1.8695ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:23:54 | 200 | 1.5804ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:24:24 | 200 | 2.8267ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:24:54 | 200 | 1.6257ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:25:24 | 200 | 1.6215ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:25:54 | 200 | 1.1228ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:26:24 | 200 | 2.3629ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:26:54 | 200 | 2.1945ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:27:24 | 200 | 1.156ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:27:54 | 200 | 2.1764ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:28:24 | 200 | 2.4375ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:28:54 | 200 | 1.4537ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:29:24 | 200 | 1.6271ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:29:54 | 200 | 1.6367ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:30:25 | 200 | 2.5413ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:30:56 | 200 | 2.2542ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:31:21 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2026/02/28 - 16:31:21 | 200 | 1.6514ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:31:22 | 200 | 850.9832ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/02/28 - 16:31:52 | 200 | 1.6015ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:32:23 | 200 | 2.1386ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:32:54 | 200 | 544.4µs | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:33:25 | 200 | 1.6493ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:33:56 | 200 | 1.8344ms | 127.0.0.1 | GET "/api/tags" time=2026-02-28T16:34:04.350+08:00 level=INFO source=download.go:179 msg="downloading 7339fa418c9a in 1 11 KB part(s)" time=2026-02-28T16:34:05.998+08:00 level=INFO source=download.go:179 msg="downloading f6417cb1e269 in 1 42 B part(s)" time=2026-02-28T16:34:07.657+08:00 level=INFO source=download.go:179 msg="downloading 9850298a701d in 1 482 B part(s)" [GIN] 2026/02/28 - 16:34:27 | 200 | 0s | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:34:29 | 200 | 15m58s | 127.0.0.1 | POST "/api/pull" [GIN] 2026/02/28 - 16:34:58 | 200 | 2.3193ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:35:29 | 200 | 1.8509ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:36:00 | 200 | 3.5136ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:36:31 | 200 | 3.4253ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:36:43 | 200 | 527.6µs | 127.0.0.1 | GET "/api/version" [GIN] 2026/02/28 - 16:36:43 | 200 | 1.0614ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:36:43 | 200 | 437.1146ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/02/28 - 16:36:46 | 200 | 1.0373ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:36:46 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2026/02/28 - 16:36:46 | 404 | 512.7µs | 127.0.0.1 | POST "/api/show" [GIN] 2026/02/28 - 16:36:46 | 200 | 337.8204ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/02/28 - 16:36:46 | 200 | 310.6224ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/02/28 - 16:36:50 | 200 | 119.8769ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/02/28 - 16:37:16 | 200 | 1.0308ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:37:17 | 200 | 1.0514ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/02/28 - 16:37:18 | 200 | 119.4887ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/02/28 - 16:37:18 | 200 | 119.5315ms | 127.0.0.1 | POST "/api/show" time=2026-02-28T16:37:18.316+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 49788" time=2026-02-28T16:37:19.273+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-02-28T16:37:19.273+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2026-02-28T16:37:19.273+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=16 efficiency=10 threads=16 time=2026-02-28T16:37:19.353+08:00 level=INFO source=server.go:247 msg="enabling flash attention" time=2026-02-28T16:37:19.354+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\Jun\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 49828" time=2026-02-28T16:37:19.361+08:00 level=INFO source=sched.go:491 msg="system memory" total="95.4 GiB" free="79.6 GiB" free_swap="85.0 GiB" time=2026-02-28T16:37:19.361+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=8680517d-0300-0000-0002-000000000000 library=Vulkan available="52.0 GiB" free="52.5 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-02-28T16:37:19.361+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1 time=2026-02-28T16:37:19.401+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine" time=2026-02-28T16:37:19.404+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:49828" time=2026-02-28T16:37:19.405+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:262144 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-28T16:37:19.442+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35moe file_type=Q4_K_M name="" description="" num_tensors=1959 num_key_values=57 load_backend: loaded CPU backend from C:\Users\Jun\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = Intel(R) Arc(TM) 140T GPU (48GB) (Intel Corporation) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none load_backend: loaded Vulkan backend from C:\Users\Jun\AppData\Local\Programs\Ollama\lib\ollama\vulkan\ggml-vulkan.dll time=2026-02-28T16:37:19.520+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000 ggml_backend_vk_get_device_memory called: luid 0x0000000000010874 ggml_dxgi_pdh_init called DXGI + PDH Initialized. Getting GPU free memory info [DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (48GB), LUID: 0x0000000000010874, Dedicated: 0.12 GB, Shared: 54.40 GB [DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000010CBE, Dedicated: 0.00 GB, Shared: 54.40 GB Integrated GPU (Intel(R) Arc(TM) 140T GPU (48GB)) with LUID 0x0000000000010874 detected. Shared Total: 58409310535.00 bytes (54.40 GB), Shared Usage: 2203336704.00 bytes (2.05 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB) ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 56340191559 total: 58543528263 time=2026-02-28T16:37:21.213+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:262144 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000 ggml_backend_vk_get_device_memory called: luid 0x0000000000010874 ggml_dxgi_pdh_init called DXGI + PDH Initialized. Getting GPU free memory info [DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (48GB), LUID: 0x0000000000010874, Dedicated: 0.12 GB, Shared: 54.40 GB [DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000010CBE, Dedicated: 0.00 GB, Shared: 54.40 GB Integrated GPU (Intel(R) Arc(TM) 140T GPU (48GB)) with LUID 0x0000000000010874 detected. Shared Total: 58409310535.00 bytes (54.40 GB), Shared Usage: 2204721152.00 bytes (2.05 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB) ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 56338807111 total: 58543528263 time=2026-02-28T16:37:26.388+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:262144 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="21.9 GiB" time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="277.3 MiB" time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="6.5 GiB" time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="3.4 GiB" time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="33.0 MiB" time=2026-02-28T16:37:26.388+08:00 level=INFO source=device.go:272 msg="total memory" size="32.2 GiB" time=2026-02-28T16:37:26.388+08:00 level=INFO source=ggml.go:482 msg="offloading 40 repeating layers to GPU" time=2026-02-28T16:37:26.388+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1 time=2026-02-28T16:37:26.388+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2026-02-28T16:37:26.388+08:00 level=INFO source=ggml.go:494 msg="offloaded 41/41 layers to GPU" time=2026-02-28T16:37:26.388+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding" time=2026-02-28T16:37:26.389+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model" [GIN] 2026/02/28 - 16:37:48 | 200 | 1.6013ms | 127.0.0.1 | GET "/api/tags" time=2026-02-28T16:37:59.687+08:00 level=INFO source=server.go:1388 msg="llama runner started in 40.33 seconds" Exception 0xc0000005 0x1 0x22e1000 0x7ffb84a5be7b PC=0x7ffb84a5be7b signal arrived during external code execution runtime.cgocall(0x7ff7ef467560, 0xc00299daa0) runtime/cgocall.go:167 +0x3e fp=0xc00299da78 sp=0xc00299da10 pc=0x7ff7ee58243e github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x1b1fad2d5c0, 0x1b24a88ac20) _cgo_gotypes.go:963 +0x50 fp=0xc00299daa0 sp=0xc00299da78 pc=0x7ff7eea85310 github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func2(...) github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify(0xc000a6a9c0, 0xc0029fadc0?, {0xc001a29a90, 0x1, 0x2?}) github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 +0x1b5 fp=0xc00299db78 sp=0xc00299daa0 pc=0x7ff7eea94bd5 github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc00055a780, {0x0, {0x7ff7efd036e0, 0xc000a6a9c0}, {0x7ff7efd134c8, 0xc0035d6348}, {0xc0029f5208, 0xa7, 0x11f}, {{0x7ff7efd134c8, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:716 +0x862 fp=0xc00299def0 sp=0xc00299db78 pc=0x7ff7eebbfa82 github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1() github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc00299dfe0 sp=0xc00299def0 pc=0x7ff7eebbd778 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00299dfe8 sp=0xc00299dfe0 pc=0x7ff7ee58d9a1 created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 13 github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd goroutine 1 gp=0xc0000021c0 m=nil [IO wait]: runtime.gopark(0x7ff7ee58f1a0?, 0x7ff7f07b92e0?, 0x20?, 0xd4?, 0xc00047d4cc?) runtime/proc.go:435 +0xce fp=0xc000383630 sp=0xc000383610 pc=0x7ff7ee58598e runtime.netpollblock(0x274?, 0xee520406?, 0xf7?) runtime/netpoll.go:575 +0xf7 fp=0xc000383668 sp=0xc000383630 pc=0x7ff7ee54bdf7 internal/poll.runtime_pollWait(0x1b1f3e8c970, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc000383688 sp=0xc000383668 pc=0x7ff7ee584b25 internal/poll.(*pollDesc).wait(0x7ff7ee61a953?, 0x0?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0003836b0 sp=0xc000383688 pc=0x7ff7ee61bf47 internal/poll.execIO(0xc00047d420, 0xc00058f758) internal/poll/fd_windows.go:177 +0x105 fp=0xc000383728 sp=0xc0003836b0 pc=0x7ff7ee61d3a5 internal/poll.(*FD).acceptOne(0xc00047d408, 0x280, {0xc00015e0f0?, 0xc00058f7b8?, 0x7ff7ee625065?}, 0xc00058f7ec?) internal/poll/fd_windows.go:946 +0x65 fp=0xc000383788 sp=0xc000383728 pc=0x7ff7ee621925 internal/poll.(*FD).Accept(0xc00047d408, 0xc000383938) internal/poll/fd_windows.go:980 +0x1b6 fp=0xc000383840 sp=0xc000383788 pc=0x7ff7ee621c56 net.(*netFD).accept(0xc00047d408) net/fd_windows.go:182 +0x4b fp=0xc000383958 sp=0xc000383840 pc=0x7ff7ee69358b net.(*TCPListener).accept(0xc00051ee00) net/tcpsock_posix.go:159 +0x1b fp=0xc0003839a8 sp=0xc000383958 pc=0x7ff7ee6a9b3b net.(*TCPListener).Accept(0xc00051ee00) net/tcpsock.go:380 +0x30 fp=0xc0003839d8 sp=0xc0003839a8 pc=0x7ff7ee6a88f0 net/http.(*onceCloseListener).Accept(0xc000142480?) <autogenerated>:1 +0x24 fp=0xc0003839f0 sp=0xc0003839d8 pc=0x7ff7ee8c1fe4 net/http.(*Server).Serve(0xc0001cfa00, {0x7ff7efcf4710, 0xc00051ee00}) net/http/server.go:3424 +0x30c fp=0xc000383b20 sp=0xc0003839f0 pc=0x7ff7ee8998ac github.com/ollama/ollama/runner/ollamarunner.Execute({0xc00004e0b0, 0x4, 0x5}) github.com/ollama/ollama/runner/ollamarunner/runner.go:1447 +0x94e fp=0xc000383cf0 sp=0xc000383b20 pc=0x7ff7eebc6a2e github.com/ollama/ollama/runner.Execute({0xc00004e090?, 0x0?, 0x0?}) github.com/ollama/ollama/runner/runner.go:18 +0x12b fp=0xc000383d30 sp=0xc000383cf0 pc=0x7ff7eebd184b github.com/ollama/ollama/cmd.NewCLI.func3(0xc0001cf600?, {0x7ff7efacd112?, 0x4?, 0x7ff7efacd116?}) github.com/ollama/ollama/cmd/cmd.go:2270 +0x45 fp=0xc000383d58 sp=0xc000383d30 pc=0x7ff7ef3f84e5 github.com/spf13/cobra.(*Command).execute(0xc000145b08, {0xc0000e1ea0, 0x5, 0x5}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000383e78 sp=0xc000383d58 pc=0x7ff7ee70e75c github.com/spf13/cobra.(*Command).ExecuteC(0xc000552f08) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000383f30 sp=0xc000383e78 pc=0x7ff7ee70efa5 github.com/spf13/cobra.(*Command).Execute(...) github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) github.com/spf13/cobra@v1.7.0/command.go:985 main.main() github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000383f50 sp=0xc000383f30 pc=0x7ff7ef3fa98d runtime.main() runtime/proc.go:283 +0x27d fp=0xc000383fe0 sp=0xc000383f50 pc=0x7ff7ee554ddd runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000383fe8 sp=0xc000383fe0 pc=0x7ff7ee58d9a1 goroutine 2 gp=0xc0000028c0 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000081fa8 sp=0xc000081f88 pc=0x7ff7ee58598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.forcegchelper() runtime/proc.go:348 +0xb8 fp=0xc000081fe0 sp=0xc000081fa8 pc=0x7ff7ee5550f8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff7ee58d9a1 created by runtime.init.7 in goroutine 1 runtime/proc.go:336 +0x1a goroutine 3 gp=0xc000002c40 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000083f80 sp=0xc000083f60 pc=0x7ff7ee58598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.bgsweep(0xc00008a000) runtime/mgcsweep.go:316 +0xdf fp=0xc000083fc8 sp=0xc000083f80 pc=0x7ff7ee53debf runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff7ee532285 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff7ee58d9a1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000002e00 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x42c1d800?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000091f78 sp=0xc000091f58 pc=0x7ff7ee58598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.(*scavengerState).park(0x7ff7f07e3080) runtime/mgcscavenge.go:425 +0x49 fp=0xc000091fa8 sp=0xc000091f78 pc=0x7ff7ee53b909 runtime.bgscavenge(0xc00008a000) runtime/mgcscavenge.go:658 +0x59 fp=0xc000091fc8 sp=0xc000091fa8 pc=0x7ff7ee53be99 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc000091fe0 sp=0xc000091fc8 pc=0x7ff7ee532225 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000091fe8 sp=0xc000091fe0 pc=0x7ff7ee58d9a1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 5 gp=0xc000003340 m=nil [finalizer wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000093e30 sp=0xc000093e10 pc=0x7ff7ee58598e runtime.runfinq() runtime/mfinal.go:196 +0x107 fp=0xc000093fe0 sp=0xc000093e30 pc=0x7ff7ee531207 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000093fe8 sp=0xc000093fe0 pc=0x7ff7ee58d9a1 created by runtime.createfing in goroutine 1 runtime/mfinal.go:166 +0x3d goroutine 6 gp=0xc000003dc0 m=nil [chan receive]: runtime.gopark(0xc0002014a0?, 0xc118080000?, 0x60?, 0x5f?, 0x7ff7ee67c1a8?) runtime/proc.go:435 +0xce fp=0xc000085f18 sp=0xc000085ef8 pc=0x7ff7ee58598e runtime.chanrecv(0xc0000983f0, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc000085f90 sp=0xc000085f18 pc=0x7ff7ee522d45 runtime.chanrecv1(0x7ff7ee554f40?, 0xc000085f76?) runtime/chan.go:506 +0x12 fp=0xc000085fb8 sp=0xc000085f90 pc=0x7ff7ee5228d2 runtime.unique_runtime_registerUniqueMapCleanup.func2(...) runtime/mgc.go:1796 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1799 +0x2f fp=0xc000085fe0 sp=0xc000085fb8 pc=0x7ff7ee5354af runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff7ee58d9a1 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1794 +0x85 goroutine 7 gp=0xc0003f8380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00008df38 sp=0xc00008df18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc00008dfc8 sp=0xc00008df38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00008dfe0 sp=0xc00008dfc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00008dfe8 sp=0xc00008dfe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 18 gp=0xc0001061c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000113f38 sp=0xc000113f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc000113fc8 sp=0xc000113f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000113fe0 sp=0xc000113fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000113fe8 sp=0xc000113fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 34 gp=0xc000484000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00010ff38 sp=0xc00010ff18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc00010ffc8 sp=0xc00010ff38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00010ffe0 sp=0xc00010ffc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00010ffe8 sp=0xc00010ffe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 35 gp=0xc0004841c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000111f38 sp=0xc000111f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc000111fc8 sp=0xc000111f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000111fe0 sp=0xc000111fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000111fe8 sp=0xc000111fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 8 gp=0xc0003f8540 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00008ff38 sp=0xc00008ff18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc00008ffc8 sp=0xc00008ff38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00008ffe0 sp=0xc00008ffc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00008ffe8 sp=0xc00008ffe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 9 gp=0xc0003f8700 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000473f38 sp=0xc000473f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc000473fc8 sp=0xc000473f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000473fe0 sp=0xc000473fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000473fe8 sp=0xc000473fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 10 gp=0xc0003f88c0 m=nil [GC worker (idle)]: runtime.gopark(0x179d1a147c9c4?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000475f38 sp=0xc000475f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc000475fc8 sp=0xc000475f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000475fe0 sp=0xc000475fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000475fe8 sp=0xc000475fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 11 gp=0xc0003f8a80 m=nil [GC worker (idle)]: runtime.gopark(0x179d0cb9c1334?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00046ff38 sp=0xc00046ff18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc00046ffc8 sp=0xc00046ff38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00046ffe0 sp=0xc00046ffc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00046ffe8 sp=0xc00046ffe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 19 gp=0xc000106380 m=nil [GC worker (idle)]: runtime.gopark(0x179d1a1501c3c?, 0x1?, 0x5c?, 0x26?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000115f38 sp=0xc000115f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc000115fc8 sp=0xc000115f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000115fe0 sp=0xc000115fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000115fe8 sp=0xc000115fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 12 gp=0xc0003f8c40 m=nil [GC worker (idle)]: runtime.gopark(0x179d1a13deb98?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000471f38 sp=0xc000471f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc000471fc8 sp=0xc000471f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000471fe0 sp=0xc000471fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000471fe8 sp=0xc000471fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 36 gp=0xc000484540 m=nil [GC worker (idle)]: runtime.gopark(0x179d1a1501c3c?, 0x1?, 0xa8?, 0x31?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000491f38 sp=0xc000491f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc000491fc8 sp=0xc000491f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000491fe0 sp=0xc000491fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000491fe8 sp=0xc000491fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 37 gp=0xc000484700 m=nil [GC worker (idle)]: runtime.gopark(0x179d0cb9c1334?, 0x1?, 0x48?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000493f38 sp=0xc000493f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc000493fc8 sp=0xc000493f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000493fe0 sp=0xc000493fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000493fe8 sp=0xc000493fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 38 gp=0xc0004848c0 m=nil [GC worker (idle)]: runtime.gopark(0x179d1a13deb98?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 39 gp=0xc000484a80 m=nil [GC worker (idle)]: runtime.gopark(0x179d1a13deb98?, 0x3?, 0xd0?, 0xba?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00048ff38 sp=0xc00048ff18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc00048ffc8 sp=0xc00048ff38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00048ffe0 sp=0xc00048ffc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048ffe8 sp=0xc00048ffe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 40 gp=0xc000484c40 m=nil [GC worker (idle)]: runtime.gopark(0x179d1a147c9c4?, 0x1?, 0x98?, 0x88?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000499f38 sp=0xc000499f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc000499fc8 sp=0xc000499f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000499fe0 sp=0xc000499fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000499fe8 sp=0xc000499fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 41 gp=0xc000484e00 m=nil [GC worker (idle)]: runtime.gopark(0x179d0cb9c1334?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00049bf38 sp=0xc00049bf18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099810) runtime/mgc.go:1423 +0xe9 fp=0xc00049bfc8 sp=0xc00049bf38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00049bfe0 sp=0xc00049bfc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00049bfe8 sp=0xc00049bfe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 13 gp=0xc000106a80 m=nil [chan receive]: runtime.gopark(0x30?, 0x7ff7efa26ba0?, 0x1?, 0x0?, 0xc0004a3798?) runtime/proc.go:435 +0xce fp=0xc0004a3750 sp=0xc0004a3730 pc=0x7ff7ee58598e runtime.chanrecv(0xc000c14310, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc0004a37c8 sp=0xc0004a3750 pc=0x7ff7ee522d45 runtime.chanrecv1(0x7ff7efb118ca?, 0x29?) runtime/chan.go:506 +0x12 fp=0xc0004a37f0 sp=0xc0004a37c8 pc=0x7ff7ee5228d2 github.com/ollama/ollama/runner/ollamarunner.(*Server).forwardBatch(_, {0x1, {0x7ff7efd036e0, 0xc00334a480}, {0x7ff7efd134c8, 0xc003604cf0}, {0xc00333a4d8, 0x1, 0x1}, {{0x7ff7efd134c8, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:476 +0xfa fp=0xc0004a3b58 sp=0xc0004a37f0 pc=0x7ff7eebbd89a github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc00055a780, {0x7ff7efcf7030, 0xc00015c000}) github.com/ollama/ollama/runner/ollamarunner/runner.go:453 +0x18c fp=0xc0004a3fb8 sp=0xc0004a3b58 pc=0x7ff7eebbd54c github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1() github.com/ollama/ollama/runner/ollamarunner/runner.go:1424 +0x28 fp=0xc0004a3fe0 sp=0xc0004a3fb8 pc=0x7ff7eebc6ca8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a3fe8 sp=0xc0004a3fe0 pc=0x7ff7ee58d9a1 created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/ollamarunner/runner.go:1424 +0x4c9 goroutine 14 gp=0xc000106c40 m=nil [select]: runtime.gopark(0xc000047a08?, 0x2?, 0xc0?, 0x77?, 0xc00004786c?) runtime/proc.go:435 +0xce fp=0xc000047698 sp=0xc000047678 pc=0x7ff7ee58598e runtime.selectgo(0xc000047a08, 0xc000047868, 0xa7?, 0x0, 0x1?, 0x1) runtime/select.go:351 +0x837 fp=0xc0000477d0 sp=0xc000047698 pc=0x7ff7ee566437 github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc00055a780, {0x7ff7efcf48c0, 0xc000b58fc0}, 0xc000b60f00) github.com/ollama/ollama/runner/ollamarunner/runner.go:956 +0xc4e fp=0xc000047ac0 sp=0xc0000477d0 pc=0x7ff7eebc1d2e github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x7ff7efcf48c0?, 0xc000b58fc0?}, 0xc000047b40?) <autogenerated>:1 +0x36 fp=0xc000047af0 sp=0xc000047ac0 pc=0x7ff7eebc7196 net/http.HandlerFunc.ServeHTTP(0xc00053c3c0?, {0x7ff7efcf48c0?, 0xc000b58fc0?}, 0xc000047b60?) net/http/server.go:2294 +0x29 fp=0xc000047b18 sp=0xc000047af0 pc=0x7ff7ee895ee9 net/http.(*ServeMux).ServeHTTP(0x7ff7ee52b785?, {0x7ff7efcf48c0, 0xc000b58fc0}, 0xc000b60f00) net/http/server.go:2822 +0x1c4 fp=0xc000047b68 sp=0xc000047b18 pc=0x7ff7ee897de4 net/http.serverHandler.ServeHTTP({0x7ff7efcf0af0?}, {0x7ff7efcf48c0?, 0xc000b58fc0?}, 0x1?) net/http/server.go:3301 +0x8e fp=0xc000047b98 sp=0xc000047b68 pc=0x7ff7ee8b586e net/http.(*conn).serve(0xc000142480, {0x7ff7efcf6ff8, 0xc000257590}) net/http/server.go:2102 +0x625 fp=0xc000047fb8 sp=0xc000047b98 pc=0x7ff7ee8943e5 net/http.(*Server).Serve.gowrap3() net/http/server.go:3454 +0x28 fp=0xc000047fe0 sp=0xc000047fb8 pc=0x7ff7ee899ca8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000047fe8 sp=0xc000047fe0 pc=0x7ff7ee58d9a1 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3454 +0x485 goroutine 2183 gp=0xc000106fc0 m=nil [IO wait]: runtime.gopark(0x0?, 0xc00047d6a0?, 0x48?, 0xd7?, 0xc00047d74c?) runtime/proc.go:435 +0xce fp=0xc0004b5d58 sp=0xc0004b5d38 pc=0x7ff7ee58598e runtime.netpollblock(0x27c?, 0xee520406?, 0xf7?) runtime/netpoll.go:575 +0xf7 fp=0xc0004b5d90 sp=0xc0004b5d58 pc=0x7ff7ee54bdf7 internal/poll.runtime_pollWait(0x1b1f3e8c858, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0004b5db0 sp=0xc0004b5d90 pc=0x7ff7ee584b25 internal/poll.(*pollDesc).wait(0x27c?, 0x72?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0004b5dd8 sp=0xc0004b5db0 pc=0x7ff7ee61bf47 internal/poll.execIO(0xc00047d6a0, 0x7ff7efb51a00) internal/poll/fd_windows.go:177 +0x105 fp=0xc0004b5e50 sp=0xc0004b5dd8 pc=0x7ff7ee61d3a5 internal/poll.(*FD).Read(0xc00047d688, {0xc0003340a1, 0x1, 0x1}) internal/poll/fd_windows.go:438 +0x29b fp=0xc0004b5ef0 sp=0xc0004b5e50 pc=0x7ff7ee61e07b net.(*netFD).Read(0xc00047d688, {0xc0003340a1?, 0xc00059e0d8?, 0xc0004b5f70?}) net/fd_posix.go:55 +0x25 fp=0xc0004b5f38 sp=0xc0004b5ef0 pc=0x7ff7ee691465 net.(*conn).Read(0xc00007a8e8, {0xc0003340a1?, 0xc0036270c0?, 0x7ff7ee914600?}) net/net.go:194 +0x45 fp=0xc0004b5f80 sp=0xc0004b5f38 pc=0x7ff7ee6a0b85 net/http.(*connReader).backgroundRead(0xc000334090) net/http/server.go:690 +0x37 fp=0xc0004b5fc8 sp=0xc0004b5f80 pc=0x7ff7ee88e2b7 net/http.(*connReader).startBackgroundRead.gowrap2() net/http/server.go:686 +0x25 fp=0xc0004b5fe0 sp=0xc0004b5fc8 pc=0x7ff7ee88e1e5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b5fe8 sp=0xc0004b5fe0 pc=0x7ff7ee58d9a1 created by net/http.(*connReader).startBackgroundRead in goroutine 14 net/http/server.go:686 +0xb6 goroutine 2238 gp=0xc000b24380 m=nil [chan receive]: runtime.gopark(0x30?, 0x7ff7efa26ba0?, 0x1?, 0xbe?, 0xc000c1bb20?) runtime/proc.go:435 +0xce fp=0xc000c1bad8 sp=0xc000c1bab8 pc=0x7ff7ee58598e runtime.chanrecv(0xc000a6e540, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc000c1bb50 sp=0xc000c1bad8 pc=0x7ff7ee522d45 runtime.chanrecv1(0x7ff7efb154d4?, 0x2c?) runtime/chan.go:506 +0x12 fp=0xc000c1bb78 sp=0xc000c1bb50 pc=0x7ff7ee5228d2 github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc00055a780, {0x1, {0x7ff7efd036e0, 0xc00334a480}, {0x7ff7efd134c8, 0xc003604cf0}, {0xc00333a4d8, 0x1, 0x1}, {{0x7ff7efd134c8, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:645 +0x185 fp=0xc000c1bef0 sp=0xc000c1bb78 pc=0x7ff7eebbf3a5 github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1() github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc000c1bfe0 sp=0xc000c1bef0 pc=0x7ff7eebbd778 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000c1bfe8 sp=0xc000c1bfe0 pc=0x7ff7ee58d9a1 created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 13 github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd rax 0x0 rbx 0x0 rcx 0x1b7e051a0e0 rdx 0x0 rdi 0x80 rsi 0x22e1060 rbp 0x1b7e051a080 rsp 0x8f715ff330 r8 0x22e1000 r9 0x0 r10 0x22e1060 r11 0x0 r12 0x0 r13 0x1b24ab15730 r14 0x0 r15 0x0 rip 0x7ffb84a5be7b rflags 0x10246 cs 0x33 fs 0x53 gs 0x2b time=2026-02-28T16:38:04.508+08:00 level=ERROR source=server.go:1610 msg="post predict" error="Post \"http://127.0.0.1:49828/completion\": read tcp 127.0.0.1:49833->127.0.0.1:49828: wsarecv: An existing connection was forcibly closed by the remote host." ``` ### OS Windows ### GPU Intel ### CPU Intel ### Ollama version 0.17.4
GiteaMirror added the bug label 2026-04-29 09:57:38 -05:00
GiteaMirror commented 2026-04-29 09:57:42 -05:00
Author
Owner
Copy Link

@junzhang-bjtu commented on GitHub (Feb 28, 2026):

I found that context length setting is too high.

<!-- gh-comment-id:3976968198 --> @junzhang-bjtu commented on GitHub (Feb 28, 2026): I found that context length setting is too high.
GiteaMirror commented 2026-04-29 09:57:43 -05:00
Author
Owner
Copy Link

@junzhang-bjtu commented on GitHub (Feb 28, 2026):

I changed the context length to 4k, but error also occured.

time=2026-02-28T19:03:12.921+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 54438"
time=2026-02-28T19:03:13.359+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-02-28T19:03:13.359+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2026-02-28T19:03:13.359+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=16 efficiency=10 threads=16
time=2026-02-28T19:03:13.479+08:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-02-28T19:03:13.481+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\Jun\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 54447"
time=2026-02-28T19:03:13.487+08:00 level=INFO source=sched.go:491 msg="system memory" total="95.4 GiB" free="80.1 GiB" free_swap="85.3 GiB"
time=2026-02-28T19:03:13.487+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=8680517d-0300-0000-0002-000000000000 library=Vulkan available="52.3 GiB" free="52.8 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-02-28T19:03:13.487+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1
time=2026-02-28T19:03:13.538+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
time=2026-02-28T19:03:13.542+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:54447"
time=2026-02-28T19:03:13.543+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-28T19:03:13.580+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35moe file_type=Q4_K_M name="" description="" num_tensors=1959 num_key_values=57
load_backend: loaded CPU backend from C:\Users\Jun\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Intel(R) Arc(TM) 140T GPU (48GB) (Intel Corporation) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none
load_backend: loaded Vulkan backend from C:\Users\Jun\AppData\Local\Programs\Ollama\lib\ollama\vulkan\ggml-vulkan.dll
time=2026-02-28T19:03:13.655+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000
ggml_backend_vk_get_device_memory called: luid 0x0000000000010874
ggml_dxgi_pdh_init called
DXGI + PDH Initialized. Getting GPU free memory info
[DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (48GB), LUID: 0x0000000000010874, Dedicated: 0.12 GB, Shared: 54.40 GB
[DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000010CBE, Dedicated: 0.00 GB, Shared: 54.40 GB
Integrated GPU (Intel(R) Arc(TM) 140T GPU (48GB)) with LUID 0x0000000000010874 detected. Shared Total: 58409310535.00 bytes (54.40 GB), Shared Usage: 1877442560.00 bytes (1.75 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB)
ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 56666085703 total: 58543528263
time=2026-02-28T19:03:14.077+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000
ggml_backend_vk_get_device_memory called: luid 0x0000000000010874
ggml_dxgi_pdh_init called
DXGI + PDH Initialized. Getting GPU free memory info
[DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (48GB), LUID: 0x0000000000010874, Dedicated: 0.12 GB, Shared: 54.40 GB
[DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000010CBE, Dedicated: 0.00 GB, Shared: 54.40 GB
Integrated GPU (Intel(R) Arc(TM) 140T GPU (48GB)) with LUID 0x0000000000010874 detected. Shared Total: 58409310535.00 bytes (54.40 GB), Shared Usage: 1877442560.00 bytes (1.75 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB)
ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 56666085703 total: 58543528263
time=2026-02-28T19:03:16.049+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="21.9 GiB"
time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="277.3 MiB"
time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="1.6 GiB"
time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="429.5 MiB"
time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="33.0 MiB"
time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:272 msg="total memory" size="24.3 GiB"
time=2026-02-28T19:03:16.049+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1
time=2026-02-28T19:03:16.049+08:00 level=INFO source=ggml.go:482 msg="offloading 40 repeating layers to GPU"
time=2026-02-28T19:03:16.049+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-02-28T19:03:16.049+08:00 level=INFO source=ggml.go:494 msg="offloaded 41/41 layers to GPU"
time=2026-02-28T19:03:16.049+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
time=2026-02-28T19:03:16.049+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model"
[GIN] 2026/02/28 - 19:03:42 | 200 |      8.2421ms |       127.0.0.1 | GET      "/api/tags"
time=2026-02-28T19:03:45.099+08:00 level=INFO source=server.go:1388 msg="llama runner started in 31.61 seconds"
Exception 0xc0000005 0x1 0x22e1000 0x7ffbceabbe7b
PC=0x7ffbceabbe7b
signal arrived during external code execution

runtime.cgocall(0x7ff7ef467560, 0xc000e63aa0)
	runtime/cgocall.go:167 +0x3e fp=0xc000e63a78 sp=0xc000e63a10 pc=0x7ff7ee58243e
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x14edb400520, 0x154bc186c20)
	_cgo_gotypes.go:963 +0x50 fp=0xc000e63aa0 sp=0xc000e63a78 pc=0x7ff7eea85310
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func2(...)
	github.com/ollama/ollama/ml/backend/ggml/ggml.go:825
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify(0xc0004b4100, 0xc0000c4dc0?, {0xc0095193d0, 0x1, 0x2?})
	github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 +0x1b5 fp=0xc000e63b78 sp=0xc000e63aa0 pc=0x7ff7eea94bd5
github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc0001850e0, {0x0, {0x7ff7efd036e0, 0xc0004b4100}, {0x7ff7efd134c8, 0xc0094fa210}, {0xc0016a1b08, 0xa7, 0x11f}, {{0x7ff7efd134c8, ...}, ...}, ...})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:716 +0x862 fp=0xc000e63ef0 sp=0xc000e63b78 pc=0x7ff7eebbfa82
github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1()
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc000e63fe0 sp=0xc000e63ef0 pc=0x7ff7eebbd778
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000e63fe8 sp=0xc000e63fe0 pc=0x7ff7ee58d9a1
created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 41
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd

goroutine 1 gp=0xc0000021c0 m=nil [IO wait]:
runtime.gopark(0x7ff7ee58f1a0?, 0x7ff7f07b92e0?, 0xa0?, 0x91?, 0xc00068924c?)
	runtime/proc.go:435 +0xce fp=0xc000e79630 sp=0xc000e79610 pc=0x7ff7ee58598e
runtime.netpollblock(0x23c?, 0xee520406?, 0xf7?)
	runtime/netpoll.go:575 +0xf7 fp=0xc000e79668 sp=0xc000e79630 pc=0x7ff7ee54bdf7
internal/poll.runtime_pollWait(0x14ed45c7d30, 0x72)
	runtime/netpoll.go:351 +0x85 fp=0xc000e79688 sp=0xc000e79668 pc=0x7ff7ee584b25
internal/poll.(*pollDesc).wait(0x7ff7ee61a953?, 0x0?, 0x0)
	internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000e796b0 sp=0xc000e79688 pc=0x7ff7ee61bf47
internal/poll.execIO(0xc0006891a0, 0xc00049d758)
	internal/poll/fd_windows.go:177 +0x105 fp=0xc000e79728 sp=0xc000e796b0 pc=0x7ff7ee61d3a5
internal/poll.(*FD).acceptOne(0xc000689188, 0x264, {0xc0006ca0f0?, 0xc00049d7b8?, 0x7ff7ee625065?}, 0xc00049d7ec?)
	internal/poll/fd_windows.go:946 +0x65 fp=0xc000e79788 sp=0xc000e79728 pc=0x7ff7ee621925
internal/poll.(*FD).Accept(0xc000689188, 0xc000e79938)
	internal/poll/fd_windows.go:980 +0x1b6 fp=0xc000e79840 sp=0xc000e79788 pc=0x7ff7ee621c56
net.(*netFD).accept(0xc000689188)
	net/fd_windows.go:182 +0x4b fp=0xc000e79958 sp=0xc000e79840 pc=0x7ff7ee69358b
net.(*TCPListener).accept(0xc0004b4c40)
	net/tcpsock_posix.go:159 +0x1b fp=0xc000e799a8 sp=0xc000e79958 pc=0x7ff7ee6a9b3b
net.(*TCPListener).Accept(0xc0004b4c40)
	net/tcpsock.go:380 +0x30 fp=0xc000e799d8 sp=0xc000e799a8 pc=0x7ff7ee6a88f0
net/http.(*onceCloseListener).Accept(0xc0006b0480?)
	<autogenerated>:1 +0x24 fp=0xc000e799f0 sp=0xc000e799d8 pc=0x7ff7ee8c1fe4
net/http.(*Server).Serve(0xc00014fa00, {0x7ff7efcf4710, 0xc0004b4c40})
	net/http/server.go:3424 +0x30c fp=0xc000e79b20 sp=0xc000e799f0 pc=0x7ff7ee8998ac
github.com/ollama/ollama/runner/ollamarunner.Execute({0xc00004e0b0, 0x4, 0x5})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:1447 +0x94e fp=0xc000e79cf0 sp=0xc000e79b20 pc=0x7ff7eebc6a2e
github.com/ollama/ollama/runner.Execute({0xc00004e090?, 0x0?, 0x0?})
	github.com/ollama/ollama/runner/runner.go:18 +0x12b fp=0xc000e79d30 sp=0xc000e79cf0 pc=0x7ff7eebd184b
github.com/ollama/ollama/cmd.NewCLI.func3(0xc00014f600?, {0x7ff7efacd112?, 0x4?, 0x7ff7efacd116?})
	github.com/ollama/ollama/cmd/cmd.go:2270 +0x45 fp=0xc000e79d58 sp=0xc000e79d30 pc=0x7ff7ef3f84e5
github.com/spf13/cobra.(*Command).execute(0xc000157508, {0xc000359d10, 0x5, 0x5})
	github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000e79e78 sp=0xc000e79d58 pc=0x7ff7ee70e75c
github.com/spf13/cobra.(*Command).ExecuteC(0xc00046ec08)
	github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000e79f30 sp=0xc000e79e78 pc=0x7ff7ee70efa5
github.com/spf13/cobra.(*Command).Execute(...)
	github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
	github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
	github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000e79f50 sp=0xc000e79f30 pc=0x7ff7ef3fa98d
runtime.main()
	runtime/proc.go:283 +0x27d fp=0xc000e79fe0 sp=0xc000e79f50 pc=0x7ff7ee554ddd
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000e79fe8 sp=0xc000e79fe0 pc=0x7ff7ee58d9a1

goroutine 2 gp=0xc0000028c0 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000081fa8 sp=0xc000081f88 pc=0x7ff7ee58598e
runtime.goparkunlock(...)
	runtime/proc.go:441
runtime.forcegchelper()
	runtime/proc.go:348 +0xb8 fp=0xc000081fe0 sp=0xc000081fa8 pc=0x7ff7ee5550f8
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff7ee58d9a1
created by runtime.init.7 in goroutine 1
	runtime/proc.go:336 +0x1a

goroutine 3 gp=0xc000002c40 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000083f80 sp=0xc000083f60 pc=0x7ff7ee58598e
runtime.goparkunlock(...)
	runtime/proc.go:441
runtime.bgsweep(0xc00008a000)
	runtime/mgcsweep.go:316 +0xdf fp=0xc000083fc8 sp=0xc000083f80 pc=0x7ff7ee53debf
runtime.gcenable.gowrap1()
	runtime/mgc.go:204 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff7ee532285
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff7ee58d9a1
created by runtime.gcenable in goroutine 1
	runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000002e00 m=nil [GC scavenge wait]:
runtime.gopark(0x340f58?, 0x74c9a7?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000091f78 sp=0xc000091f58 pc=0x7ff7ee58598e
runtime.goparkunlock(...)
	runtime/proc.go:441
runtime.(*scavengerState).park(0x7ff7f07e3080)
	runtime/mgcscavenge.go:425 +0x49 fp=0xc000091fa8 sp=0xc000091f78 pc=0x7ff7ee53b909
runtime.bgscavenge(0xc00008a000)
	runtime/mgcscavenge.go:658 +0x59 fp=0xc000091fc8 sp=0xc000091fa8 pc=0x7ff7ee53be99
runtime.gcenable.gowrap2()
	runtime/mgc.go:205 +0x25 fp=0xc000091fe0 sp=0xc000091fc8 pc=0x7ff7ee532225
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000091fe8 sp=0xc000091fe0 pc=0x7ff7ee58d9a1
created by runtime.gcenable in goroutine 1
	runtime/mgc.go:205 +0xa5

goroutine 5 gp=0xc000003340 m=nil [finalizer wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000093e30 sp=0xc000093e10 pc=0x7ff7ee58598e
runtime.runfinq()
	runtime/mfinal.go:196 +0x107 fp=0xc000093fe0 sp=0xc000093e30 pc=0x7ff7ee531207
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000093fe8 sp=0xc000093fe0 pc=0x7ff7ee58d9a1
created by runtime.createfing in goroutine 1
	runtime/mfinal.go:166 +0x3d

goroutine 6 gp=0xc000003dc0 m=nil [chan receive]:
runtime.gopark(0xc000181680?, 0xc00942c018?, 0x60?, 0x5f?, 0x7ff7ee67c1a8?)
	runtime/proc.go:435 +0xce fp=0xc000085f18 sp=0xc000085ef8 pc=0x7ff7ee58598e
runtime.chanrecv(0xc0000983f0, 0x0, 0x1)
	runtime/chan.go:664 +0x445 fp=0xc000085f90 sp=0xc000085f18 pc=0x7ff7ee522d45
runtime.chanrecv1(0x7ff7ee554f40?, 0xc000085f76?)
	runtime/chan.go:506 +0x12 fp=0xc000085fb8 sp=0xc000085f90 pc=0x7ff7ee5228d2
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
	runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
	runtime/mgc.go:1799 +0x2f fp=0xc000085fe0 sp=0xc000085fb8 pc=0x7ff7ee5354af
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff7ee58d9a1
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
	runtime/mgc.go:1794 +0x85

goroutine 7 gp=0xc0003f81c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00008df38 sp=0xc00008df18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc00008dfc8 sp=0xc00008df38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00008dfe0 sp=0xc00008dfc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00008dfe8 sp=0xc00008dfe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 18 gp=0xc0002081c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000213f38 sp=0xc000213f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc000213fc8 sp=0xc000213f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000213fe0 sp=0xc000213fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000213fe8 sp=0xc000213fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 19 gp=0xc000208380 m=nil [GC worker (idle)]:
runtime.gopark(0x181ce893785f4?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000215f38 sp=0xc000215f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc000215fc8 sp=0xc000215f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000215fe0 sp=0xc000215fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000215fe8 sp=0xc000215fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 20 gp=0xc000208540 m=nil [GC worker (idle)]:
runtime.gopark(0x181ce89475f60?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00020ff38 sp=0xc00020ff18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc00020ffc8 sp=0xc00020ff38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00020ffe0 sp=0xc00020ffc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00020ffe8 sp=0xc00020ffe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 34 gp=0xc000484000 m=nil [GC worker (idle)]:
runtime.gopark(0x7ff7f08360e0?, 0x1?, 0xfc?, 0xdf?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00048bf38 sp=0xc00048bf18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc00048bfc8 sp=0xc00048bf38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00048bfe0 sp=0xc00048bfc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00048bfe8 sp=0xc00048bfe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 35 gp=0xc0004841c0 m=nil [GC worker (idle)]:
runtime.gopark(0x181ce893785f4?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 36 gp=0xc000484380 m=nil [GC worker (idle)]:
runtime.gopark(0x181ce893785f4?, 0x1?, 0x1c?, 0xc6?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000487f38 sp=0xc000487f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc000487fc8 sp=0xc000487f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000487fe0 sp=0xc000487fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000487fe8 sp=0xc000487fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 37 gp=0xc000484540 m=nil [GC worker (idle)]:
runtime.gopark(0x181ce89475f60?, 0x3?, 0x68?, 0xf9?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000489f38 sp=0xc000489f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc000489fc8 sp=0xc000489f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000489fe0 sp=0xc000489fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000489fe8 sp=0xc000489fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 8 gp=0xc0003f8380 m=nil [GC worker (idle)]:
runtime.gopark(0x181ce89475f60?, 0x3?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00008ff38 sp=0xc00008ff18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc00008ffc8 sp=0xc00008ff38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00008ffe0 sp=0xc00008ffc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00008ffe8 sp=0xc00008ffe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 21 gp=0xc000208700 m=nil [GC worker (idle)]:
runtime.gopark(0x181ce89475f60?, 0x1?, 0x5c?, 0xe1?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000211f38 sp=0xc000211f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc000211fc8 sp=0xc000211f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000211fe0 sp=0xc000211fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000211fe8 sp=0xc000211fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 38 gp=0xc000484700 m=nil [GC worker (idle)]:
runtime.gopark(0x7ff7f08360e0?, 0x1?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000493f38 sp=0xc000493f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc000493fc8 sp=0xc000493f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000493fe0 sp=0xc000493fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000493fe8 sp=0xc000493fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 39 gp=0xc0004848c0 m=nil [GC worker (idle)]:
runtime.gopark(0x7ff7f08360e0?, 0x1?, 0x90?, 0x6?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000495f38 sp=0xc000495f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc000495fc8 sp=0xc000495f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000495fe0 sp=0xc000495fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000495fe8 sp=0xc000495fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 9 gp=0xc0003f8540 m=nil [GC worker (idle)]:
runtime.gopark(0x181ce893785f4?, 0x3?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00048ff38 sp=0xc00048ff18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc00048ffc8 sp=0xc00048ff38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00048ffe0 sp=0xc00048ffc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00048ffe8 sp=0xc00048ffe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 22 gp=0xc0002088c0 m=nil [GC worker (idle)]:
runtime.gopark(0x181ce89475f60?, 0x1?, 0x6c?, 0xd9?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00021ff38 sp=0xc00021ff18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc00021ffc8 sp=0xc00021ff38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00021ffe0 sp=0xc00021ffc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00021ffe8 sp=0xc00021ffe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 40 gp=0xc000484a80 m=nil [GC worker (idle)]:
runtime.gopark(0x181ce89475f60?, 0x1?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00021bf38 sp=0xc00021bf18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc00021bfc8 sp=0xc00021bf38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00021bfe0 sp=0xc00021bfc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00021bfe8 sp=0xc00021bfe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 10 gp=0xc0003f8700 m=nil [GC worker (idle)]:
runtime.gopark(0x181ce893785f4?, 0x3?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000491f38 sp=0xc000491f18 pc=0x7ff7ee58598e
runtime.gcBgMarkWorker(0xc000099b90)
	runtime/mgc.go:1423 +0xe9 fp=0xc000491fc8 sp=0xc000491f38 pc=0x7ff7ee5347a9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000491fe0 sp=0xc000491fc8 pc=0x7ff7ee534685
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000491fe8 sp=0xc000491fe0 pc=0x7ff7ee58d9a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 41 gp=0xc0003f8fc0 m=nil [chan receive]:
runtime.gopark(0x30?, 0x7ff7efa26ba0?, 0x1?, 0x0?, 0xc000195798?)
	runtime/proc.go:435 +0xce fp=0xc000195750 sp=0xc000195730 pc=0x7ff7ee58598e
runtime.chanrecv(0xc001746700, 0x0, 0x1)
	runtime/chan.go:664 +0x445 fp=0xc0001957c8 sp=0xc000195750 pc=0x7ff7ee522d45
runtime.chanrecv1(0x7ff7efb118ca?, 0x29?)
	runtime/chan.go:506 +0x12 fp=0xc0001957f0 sp=0xc0001957c8 pc=0x7ff7ee5228d2
github.com/ollama/ollama/runner/ollamarunner.(*Server).forwardBatch(_, {0x1, {0x7ff7efd036e0, 0xc0093cc040}, {0x7ff7efd134c8, 0xc000557dd0}, {0xc0019ce008, 0x1, 0x1}, {{0x7ff7efd134c8, ...}, ...}, ...})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:476 +0xfa fp=0xc000195b58 sp=0xc0001957f0 pc=0x7ff7eebbd89a
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0001850e0, {0x7ff7efcf7030, 0xc000359db0})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:453 +0x18c fp=0xc000195fb8 sp=0xc000195b58 pc=0x7ff7eebbd54c
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
	github.com/ollama/ollama/runner/ollamarunner/runner.go:1424 +0x28 fp=0xc000195fe0 sp=0xc000195fb8 pc=0x7ff7eebc6ca8
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000195fe8 sp=0xc000195fe0 pc=0x7ff7ee58d9a1
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
	github.com/ollama/ollama/runner/ollamarunner/runner.go:1424 +0x4c9

goroutine 42 gp=0xc0003f9180 m=nil [select]:
runtime.gopark(0xc000047a08?, 0x2?, 0xc0?, 0x77?, 0xc00004786c?)
	runtime/proc.go:435 +0xce fp=0xc000047698 sp=0xc000047678 pc=0x7ff7ee58598e
runtime.selectgo(0xc000047a08, 0xc000047868, 0xa7?, 0x0, 0x1?, 0x1)
	runtime/select.go:351 +0x837 fp=0xc0000477d0 sp=0xc000047698 pc=0x7ff7ee566437
github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc0001850e0, {0x7ff7efcf48c0, 0xc0003960e0}, 0xc0001a2280)
	github.com/ollama/ollama/runner/ollamarunner/runner.go:956 +0xc4e fp=0xc000047ac0 sp=0xc0000477d0 pc=0x7ff7eebc1d2e
github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x7ff7efcf48c0?, 0xc0003960e0?}, 0xc000047b40?)
	<autogenerated>:1 +0x36 fp=0xc000047af0 sp=0xc000047ac0 pc=0x7ff7eebc7196
net/http.HandlerFunc.ServeHTTP(0xc0004ad500?, {0x7ff7efcf48c0?, 0xc0003960e0?}, 0xc000047b60?)
	net/http/server.go:2294 +0x29 fp=0xc000047b18 sp=0xc000047af0 pc=0x7ff7ee895ee9
net/http.(*ServeMux).ServeHTTP(0x7ff7ee52b785?, {0x7ff7efcf48c0, 0xc0003960e0}, 0xc0001a2280)
	net/http/server.go:2822 +0x1c4 fp=0xc000047b68 sp=0xc000047b18 pc=0x7ff7ee897de4
net/http.serverHandler.ServeHTTP({0x7ff7efcf0af0?}, {0x7ff7efcf48c0?, 0xc0003960e0?}, 0x1?)
	net/http/server.go:3301 +0x8e fp=0xc000047b98 sp=0xc000047b68 pc=0x7ff7ee8b586e
net/http.(*conn).serve(0xc0006b0480, {0x7ff7efcf6ff8, 0xc0006ae9f0})
	net/http/server.go:2102 +0x625 fp=0xc000047fb8 sp=0xc000047b98 pc=0x7ff7ee8943e5
net/http.(*Server).Serve.gowrap3()
	net/http/server.go:3454 +0x28 fp=0xc000047fe0 sp=0xc000047fb8 pc=0x7ff7ee899ca8
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000047fe8 sp=0xc000047fe0 pc=0x7ff7ee58d9a1
created by net/http.(*Server).Serve in goroutine 1
	net/http/server.go:3454 +0x485

goroutine 2209 gp=0xc0005068c0 m=nil [IO wait]:
runtime.gopark(0x0?, 0xc000689420?, 0xc8?, 0x94?, 0xc0006894cc?)
	runtime/proc.go:435 +0xce fp=0xc000e67d58 sp=0xc000e67d38 pc=0x7ff7ee58598e
runtime.netpollblock(0x260?, 0xee520406?, 0xf7?)
	runtime/netpoll.go:575 +0xf7 fp=0xc000e67d90 sp=0xc000e67d58 pc=0x7ff7ee54bdf7
internal/poll.runtime_pollWait(0x14ed45c7c18, 0x72)
	runtime/netpoll.go:351 +0x85 fp=0xc000e67db0 sp=0xc000e67d90 pc=0x7ff7ee584b25
internal/poll.(*pollDesc).wait(0x260?, 0x72?, 0x0)
	internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000e67dd8 sp=0xc000e67db0 pc=0x7ff7ee61bf47
internal/poll.execIO(0xc000689420, 0x7ff7efb51a00)
	internal/poll/fd_windows.go:177 +0x105 fp=0xc000e67e50 sp=0xc000e67dd8 pc=0x7ff7ee61d3a5
internal/poll.(*FD).Read(0xc000689408, {0xc0006aeaf1, 0x1, 0x1})
	internal/poll/fd_windows.go:438 +0x29b fp=0xc000e67ef0 sp=0xc000e67e50 pc=0x7ff7ee61e07b
net.(*netFD).Read(0xc000689408, {0xc0006aeaf1?, 0xc0004b4d18?, 0xc000e67f70?})
	net/fd_posix.go:55 +0x25 fp=0xc000e67f38 sp=0xc000e67ef0 pc=0x7ff7ee691465
net.(*conn).Read(0xc00007a7f0, {0xc0006aeaf1?, 0x0?, 0x7ff7efcfdc50?})
	net/net.go:194 +0x45 fp=0xc000e67f80 sp=0xc000e67f38 pc=0x7ff7ee6a0b85
net/http.(*connReader).backgroundRead(0xc0006aeae0)
	net/http/server.go:690 +0x37 fp=0xc000e67fc8 sp=0xc000e67f80 pc=0x7ff7ee88e2b7
net/http.(*connReader).startBackgroundRead.gowrap2()
	net/http/server.go:686 +0x25 fp=0xc000e67fe0 sp=0xc000e67fc8 pc=0x7ff7ee88e1e5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000e67fe8 sp=0xc000e67fe0 pc=0x7ff7ee58d9a1
created by net/http.(*connReader).startBackgroundRead in goroutine 42
	net/http/server.go:686 +0xb6

goroutine 1566 gp=0xc00090a8c0 m=nil [chan receive]:
runtime.gopark(0x30?, 0x7ff7efa26ba0?, 0x1?, 0x9d?, 0xc000221b20?)
	runtime/proc.go:435 +0xce fp=0xc000221ad8 sp=0xc000221ab8 pc=0x7ff7ee58598e
runtime.chanrecv(0xc000098310, 0x0, 0x1)
	runtime/chan.go:664 +0x445 fp=0xc000221b50 sp=0xc000221ad8 pc=0x7ff7ee522d45
runtime.chanrecv1(0x7ff7efb154d4?, 0x2c?)
	runtime/chan.go:506 +0x12 fp=0xc000221b78 sp=0xc000221b50 pc=0x7ff7ee5228d2
github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc0001850e0, {0x1, {0x7ff7efd036e0, 0xc0093cc040}, {0x7ff7efd134c8, 0xc000557dd0}, {0xc0019ce008, 0x1, 0x1}, {{0x7ff7efd134c8, ...}, ...}, ...})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:645 +0x185 fp=0xc000221ef0 sp=0xc000221b78 pc=0x7ff7eebbf3a5
github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1()
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc000221fe0 sp=0xc000221ef0 pc=0x7ff7eebbd778
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000221fe8 sp=0xc000221fe0 pc=0x7ff7ee58d9a1
created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 41
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd
rax     0x0
rbx     0x0
rcx     0x154c24660e0
rdx     0x0
rdi     0x80
rsi     0x22e1060
rbp     0x154c2466080
rsp     0x133f0ff1f0
r8      0x22e1000
r9      0x0
r10     0x22e1060
r11     0x0
r12     0x0
r13     0x154bc411730
r14     0x0
r15     0x0
rip     0x7ffbceabbe7b
rflags  0x10246
cs      0x33
fs      0x53
gs      0x2b
time=2026-02-28T19:03:47.437+08:00 level=ERROR source=server.go:1610 msg="post predict" error="Post \"http://127.0.0.1:54447/completion\": read tcp 127.0.0.1:54453->127.0.0.1:54447: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2026/02/28 - 19:03:47 | 500 |   34.6100787s |       127.0.0.1 | POST     "/api/chat"
<!-- gh-comment-id:3977011916 --> @junzhang-bjtu commented on GitHub (Feb 28, 2026): I changed the context length to 4k, but error also occured. ``` time=2026-02-28T19:03:12.921+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 54438" time=2026-02-28T19:03:13.359+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-02-28T19:03:13.359+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2026-02-28T19:03:13.359+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=16 efficiency=10 threads=16 time=2026-02-28T19:03:13.479+08:00 level=INFO source=server.go:247 msg="enabling flash attention" time=2026-02-28T19:03:13.481+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\Jun\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\Jun\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 54447" time=2026-02-28T19:03:13.487+08:00 level=INFO source=sched.go:491 msg="system memory" total="95.4 GiB" free="80.1 GiB" free_swap="85.3 GiB" time=2026-02-28T19:03:13.487+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=8680517d-0300-0000-0002-000000000000 library=Vulkan available="52.3 GiB" free="52.8 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-02-28T19:03:13.487+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1 time=2026-02-28T19:03:13.538+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine" time=2026-02-28T19:03:13.542+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:54447" time=2026-02-28T19:03:13.543+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-28T19:03:13.580+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35moe file_type=Q4_K_M name="" description="" num_tensors=1959 num_key_values=57 load_backend: loaded CPU backend from C:\Users\Jun\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = Intel(R) Arc(TM) 140T GPU (48GB) (Intel Corporation) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none load_backend: loaded Vulkan backend from C:\Users\Jun\AppData\Local\Programs\Ollama\lib\ollama\vulkan\ggml-vulkan.dll time=2026-02-28T19:03:13.655+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000 ggml_backend_vk_get_device_memory called: luid 0x0000000000010874 ggml_dxgi_pdh_init called DXGI + PDH Initialized. Getting GPU free memory info [DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (48GB), LUID: 0x0000000000010874, Dedicated: 0.12 GB, Shared: 54.40 GB [DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000010CBE, Dedicated: 0.00 GB, Shared: 54.40 GB Integrated GPU (Intel(R) Arc(TM) 140T GPU (48GB)) with LUID 0x0000000000010874 detected. Shared Total: 58409310535.00 bytes (54.40 GB), Shared Usage: 1877442560.00 bytes (1.75 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB) ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 56666085703 total: 58543528263 time=2026-02-28T19:03:14.077+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000 ggml_backend_vk_get_device_memory called: luid 0x0000000000010874 ggml_dxgi_pdh_init called DXGI + PDH Initialized. Getting GPU free memory info [DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (48GB), LUID: 0x0000000000010874, Dedicated: 0.12 GB, Shared: 54.40 GB [DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000010CBE, Dedicated: 0.00 GB, Shared: 54.40 GB Integrated GPU (Intel(R) Arc(TM) 140T GPU (48GB)) with LUID 0x0000000000010874 detected. Shared Total: 58409310535.00 bytes (54.40 GB), Shared Usage: 1877442560.00 bytes (1.75 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB) ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 56666085703 total: 58543528263 time=2026-02-28T19:03:16.049+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:41[ID:8680517d-0300-0000-0002-000000000000 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="21.9 GiB" time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="277.3 MiB" time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="1.6 GiB" time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="429.5 MiB" time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="33.0 MiB" time=2026-02-28T19:03:16.049+08:00 level=INFO source=device.go:272 msg="total memory" size="24.3 GiB" time=2026-02-28T19:03:16.049+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1 time=2026-02-28T19:03:16.049+08:00 level=INFO source=ggml.go:482 msg="offloading 40 repeating layers to GPU" time=2026-02-28T19:03:16.049+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2026-02-28T19:03:16.049+08:00 level=INFO source=ggml.go:494 msg="offloaded 41/41 layers to GPU" time=2026-02-28T19:03:16.049+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding" time=2026-02-28T19:03:16.049+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model" [GIN] 2026/02/28 - 19:03:42 | 200 | 8.2421ms | 127.0.0.1 | GET "/api/tags" time=2026-02-28T19:03:45.099+08:00 level=INFO source=server.go:1388 msg="llama runner started in 31.61 seconds" Exception 0xc0000005 0x1 0x22e1000 0x7ffbceabbe7b PC=0x7ffbceabbe7b signal arrived during external code execution runtime.cgocall(0x7ff7ef467560, 0xc000e63aa0) runtime/cgocall.go:167 +0x3e fp=0xc000e63a78 sp=0xc000e63a10 pc=0x7ff7ee58243e github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x14edb400520, 0x154bc186c20) _cgo_gotypes.go:963 +0x50 fp=0xc000e63aa0 sp=0xc000e63a78 pc=0x7ff7eea85310 github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func2(...) github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify(0xc0004b4100, 0xc0000c4dc0?, {0xc0095193d0, 0x1, 0x2?}) github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 +0x1b5 fp=0xc000e63b78 sp=0xc000e63aa0 pc=0x7ff7eea94bd5 github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc0001850e0, {0x0, {0x7ff7efd036e0, 0xc0004b4100}, {0x7ff7efd134c8, 0xc0094fa210}, {0xc0016a1b08, 0xa7, 0x11f}, {{0x7ff7efd134c8, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:716 +0x862 fp=0xc000e63ef0 sp=0xc000e63b78 pc=0x7ff7eebbfa82 github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1() github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc000e63fe0 sp=0xc000e63ef0 pc=0x7ff7eebbd778 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000e63fe8 sp=0xc000e63fe0 pc=0x7ff7ee58d9a1 created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 41 github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd goroutine 1 gp=0xc0000021c0 m=nil [IO wait]: runtime.gopark(0x7ff7ee58f1a0?, 0x7ff7f07b92e0?, 0xa0?, 0x91?, 0xc00068924c?) runtime/proc.go:435 +0xce fp=0xc000e79630 sp=0xc000e79610 pc=0x7ff7ee58598e runtime.netpollblock(0x23c?, 0xee520406?, 0xf7?) runtime/netpoll.go:575 +0xf7 fp=0xc000e79668 sp=0xc000e79630 pc=0x7ff7ee54bdf7 internal/poll.runtime_pollWait(0x14ed45c7d30, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc000e79688 sp=0xc000e79668 pc=0x7ff7ee584b25 internal/poll.(*pollDesc).wait(0x7ff7ee61a953?, 0x0?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000e796b0 sp=0xc000e79688 pc=0x7ff7ee61bf47 internal/poll.execIO(0xc0006891a0, 0xc00049d758) internal/poll/fd_windows.go:177 +0x105 fp=0xc000e79728 sp=0xc000e796b0 pc=0x7ff7ee61d3a5 internal/poll.(*FD).acceptOne(0xc000689188, 0x264, {0xc0006ca0f0?, 0xc00049d7b8?, 0x7ff7ee625065?}, 0xc00049d7ec?) internal/poll/fd_windows.go:946 +0x65 fp=0xc000e79788 sp=0xc000e79728 pc=0x7ff7ee621925 internal/poll.(*FD).Accept(0xc000689188, 0xc000e79938) internal/poll/fd_windows.go:980 +0x1b6 fp=0xc000e79840 sp=0xc000e79788 pc=0x7ff7ee621c56 net.(*netFD).accept(0xc000689188) net/fd_windows.go:182 +0x4b fp=0xc000e79958 sp=0xc000e79840 pc=0x7ff7ee69358b net.(*TCPListener).accept(0xc0004b4c40) net/tcpsock_posix.go:159 +0x1b fp=0xc000e799a8 sp=0xc000e79958 pc=0x7ff7ee6a9b3b net.(*TCPListener).Accept(0xc0004b4c40) net/tcpsock.go:380 +0x30 fp=0xc000e799d8 sp=0xc000e799a8 pc=0x7ff7ee6a88f0 net/http.(*onceCloseListener).Accept(0xc0006b0480?) <autogenerated>:1 +0x24 fp=0xc000e799f0 sp=0xc000e799d8 pc=0x7ff7ee8c1fe4 net/http.(*Server).Serve(0xc00014fa00, {0x7ff7efcf4710, 0xc0004b4c40}) net/http/server.go:3424 +0x30c fp=0xc000e79b20 sp=0xc000e799f0 pc=0x7ff7ee8998ac github.com/ollama/ollama/runner/ollamarunner.Execute({0xc00004e0b0, 0x4, 0x5}) github.com/ollama/ollama/runner/ollamarunner/runner.go:1447 +0x94e fp=0xc000e79cf0 sp=0xc000e79b20 pc=0x7ff7eebc6a2e github.com/ollama/ollama/runner.Execute({0xc00004e090?, 0x0?, 0x0?}) github.com/ollama/ollama/runner/runner.go:18 +0x12b fp=0xc000e79d30 sp=0xc000e79cf0 pc=0x7ff7eebd184b github.com/ollama/ollama/cmd.NewCLI.func3(0xc00014f600?, {0x7ff7efacd112?, 0x4?, 0x7ff7efacd116?}) github.com/ollama/ollama/cmd/cmd.go:2270 +0x45 fp=0xc000e79d58 sp=0xc000e79d30 pc=0x7ff7ef3f84e5 github.com/spf13/cobra.(*Command).execute(0xc000157508, {0xc000359d10, 0x5, 0x5}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000e79e78 sp=0xc000e79d58 pc=0x7ff7ee70e75c github.com/spf13/cobra.(*Command).ExecuteC(0xc00046ec08) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000e79f30 sp=0xc000e79e78 pc=0x7ff7ee70efa5 github.com/spf13/cobra.(*Command).Execute(...) github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) github.com/spf13/cobra@v1.7.0/command.go:985 main.main() github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000e79f50 sp=0xc000e79f30 pc=0x7ff7ef3fa98d runtime.main() runtime/proc.go:283 +0x27d fp=0xc000e79fe0 sp=0xc000e79f50 pc=0x7ff7ee554ddd runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000e79fe8 sp=0xc000e79fe0 pc=0x7ff7ee58d9a1 goroutine 2 gp=0xc0000028c0 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000081fa8 sp=0xc000081f88 pc=0x7ff7ee58598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.forcegchelper() runtime/proc.go:348 +0xb8 fp=0xc000081fe0 sp=0xc000081fa8 pc=0x7ff7ee5550f8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff7ee58d9a1 created by runtime.init.7 in goroutine 1 runtime/proc.go:336 +0x1a goroutine 3 gp=0xc000002c40 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000083f80 sp=0xc000083f60 pc=0x7ff7ee58598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.bgsweep(0xc00008a000) runtime/mgcsweep.go:316 +0xdf fp=0xc000083fc8 sp=0xc000083f80 pc=0x7ff7ee53debf runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff7ee532285 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff7ee58d9a1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000002e00 m=nil [GC scavenge wait]: runtime.gopark(0x340f58?, 0x74c9a7?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000091f78 sp=0xc000091f58 pc=0x7ff7ee58598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.(*scavengerState).park(0x7ff7f07e3080) runtime/mgcscavenge.go:425 +0x49 fp=0xc000091fa8 sp=0xc000091f78 pc=0x7ff7ee53b909 runtime.bgscavenge(0xc00008a000) runtime/mgcscavenge.go:658 +0x59 fp=0xc000091fc8 sp=0xc000091fa8 pc=0x7ff7ee53be99 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc000091fe0 sp=0xc000091fc8 pc=0x7ff7ee532225 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000091fe8 sp=0xc000091fe0 pc=0x7ff7ee58d9a1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 5 gp=0xc000003340 m=nil [finalizer wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000093e30 sp=0xc000093e10 pc=0x7ff7ee58598e runtime.runfinq() runtime/mfinal.go:196 +0x107 fp=0xc000093fe0 sp=0xc000093e30 pc=0x7ff7ee531207 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000093fe8 sp=0xc000093fe0 pc=0x7ff7ee58d9a1 created by runtime.createfing in goroutine 1 runtime/mfinal.go:166 +0x3d goroutine 6 gp=0xc000003dc0 m=nil [chan receive]: runtime.gopark(0xc000181680?, 0xc00942c018?, 0x60?, 0x5f?, 0x7ff7ee67c1a8?) runtime/proc.go:435 +0xce fp=0xc000085f18 sp=0xc000085ef8 pc=0x7ff7ee58598e runtime.chanrecv(0xc0000983f0, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc000085f90 sp=0xc000085f18 pc=0x7ff7ee522d45 runtime.chanrecv1(0x7ff7ee554f40?, 0xc000085f76?) runtime/chan.go:506 +0x12 fp=0xc000085fb8 sp=0xc000085f90 pc=0x7ff7ee5228d2 runtime.unique_runtime_registerUniqueMapCleanup.func2(...) runtime/mgc.go:1796 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1799 +0x2f fp=0xc000085fe0 sp=0xc000085fb8 pc=0x7ff7ee5354af runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff7ee58d9a1 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1794 +0x85 goroutine 7 gp=0xc0003f81c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00008df38 sp=0xc00008df18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc00008dfc8 sp=0xc00008df38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00008dfe0 sp=0xc00008dfc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00008dfe8 sp=0xc00008dfe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 18 gp=0xc0002081c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000213f38 sp=0xc000213f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc000213fc8 sp=0xc000213f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000213fe0 sp=0xc000213fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000213fe8 sp=0xc000213fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 19 gp=0xc000208380 m=nil [GC worker (idle)]: runtime.gopark(0x181ce893785f4?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000215f38 sp=0xc000215f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc000215fc8 sp=0xc000215f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000215fe0 sp=0xc000215fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000215fe8 sp=0xc000215fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 20 gp=0xc000208540 m=nil [GC worker (idle)]: runtime.gopark(0x181ce89475f60?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00020ff38 sp=0xc00020ff18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc00020ffc8 sp=0xc00020ff38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00020ffe0 sp=0xc00020ffc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00020ffe8 sp=0xc00020ffe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 34 gp=0xc000484000 m=nil [GC worker (idle)]: runtime.gopark(0x7ff7f08360e0?, 0x1?, 0xfc?, 0xdf?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00048bf38 sp=0xc00048bf18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc00048bfc8 sp=0xc00048bf38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00048bfe0 sp=0xc00048bfc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048bfe8 sp=0xc00048bfe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 35 gp=0xc0004841c0 m=nil [GC worker (idle)]: runtime.gopark(0x181ce893785f4?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 36 gp=0xc000484380 m=nil [GC worker (idle)]: runtime.gopark(0x181ce893785f4?, 0x1?, 0x1c?, 0xc6?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000487f38 sp=0xc000487f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc000487fc8 sp=0xc000487f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000487fe0 sp=0xc000487fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000487fe8 sp=0xc000487fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 37 gp=0xc000484540 m=nil [GC worker (idle)]: runtime.gopark(0x181ce89475f60?, 0x3?, 0x68?, 0xf9?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000489f38 sp=0xc000489f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc000489fc8 sp=0xc000489f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000489fe0 sp=0xc000489fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000489fe8 sp=0xc000489fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 8 gp=0xc0003f8380 m=nil [GC worker (idle)]: runtime.gopark(0x181ce89475f60?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00008ff38 sp=0xc00008ff18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc00008ffc8 sp=0xc00008ff38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00008ffe0 sp=0xc00008ffc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00008ffe8 sp=0xc00008ffe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 21 gp=0xc000208700 m=nil [GC worker (idle)]: runtime.gopark(0x181ce89475f60?, 0x1?, 0x5c?, 0xe1?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000211f38 sp=0xc000211f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc000211fc8 sp=0xc000211f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000211fe0 sp=0xc000211fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000211fe8 sp=0xc000211fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 38 gp=0xc000484700 m=nil [GC worker (idle)]: runtime.gopark(0x7ff7f08360e0?, 0x1?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000493f38 sp=0xc000493f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc000493fc8 sp=0xc000493f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000493fe0 sp=0xc000493fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000493fe8 sp=0xc000493fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 39 gp=0xc0004848c0 m=nil [GC worker (idle)]: runtime.gopark(0x7ff7f08360e0?, 0x1?, 0x90?, 0x6?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000495f38 sp=0xc000495f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc000495fc8 sp=0xc000495f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000495fe0 sp=0xc000495fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000495fe8 sp=0xc000495fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 9 gp=0xc0003f8540 m=nil [GC worker (idle)]: runtime.gopark(0x181ce893785f4?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00048ff38 sp=0xc00048ff18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc00048ffc8 sp=0xc00048ff38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00048ffe0 sp=0xc00048ffc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048ffe8 sp=0xc00048ffe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 22 gp=0xc0002088c0 m=nil [GC worker (idle)]: runtime.gopark(0x181ce89475f60?, 0x1?, 0x6c?, 0xd9?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00021ff38 sp=0xc00021ff18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc00021ffc8 sp=0xc00021ff38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00021ffe0 sp=0xc00021ffc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00021ffe8 sp=0xc00021ffe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 40 gp=0xc000484a80 m=nil [GC worker (idle)]: runtime.gopark(0x181ce89475f60?, 0x1?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00021bf38 sp=0xc00021bf18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc00021bfc8 sp=0xc00021bf38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00021bfe0 sp=0xc00021bfc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00021bfe8 sp=0xc00021bfe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 10 gp=0xc0003f8700 m=nil [GC worker (idle)]: runtime.gopark(0x181ce893785f4?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000491f38 sp=0xc000491f18 pc=0x7ff7ee58598e runtime.gcBgMarkWorker(0xc000099b90) runtime/mgc.go:1423 +0xe9 fp=0xc000491fc8 sp=0xc000491f38 pc=0x7ff7ee5347a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000491fe0 sp=0xc000491fc8 pc=0x7ff7ee534685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000491fe8 sp=0xc000491fe0 pc=0x7ff7ee58d9a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 41 gp=0xc0003f8fc0 m=nil [chan receive]: runtime.gopark(0x30?, 0x7ff7efa26ba0?, 0x1?, 0x0?, 0xc000195798?) runtime/proc.go:435 +0xce fp=0xc000195750 sp=0xc000195730 pc=0x7ff7ee58598e runtime.chanrecv(0xc001746700, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc0001957c8 sp=0xc000195750 pc=0x7ff7ee522d45 runtime.chanrecv1(0x7ff7efb118ca?, 0x29?) runtime/chan.go:506 +0x12 fp=0xc0001957f0 sp=0xc0001957c8 pc=0x7ff7ee5228d2 github.com/ollama/ollama/runner/ollamarunner.(*Server).forwardBatch(_, {0x1, {0x7ff7efd036e0, 0xc0093cc040}, {0x7ff7efd134c8, 0xc000557dd0}, {0xc0019ce008, 0x1, 0x1}, {{0x7ff7efd134c8, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:476 +0xfa fp=0xc000195b58 sp=0xc0001957f0 pc=0x7ff7eebbd89a github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0001850e0, {0x7ff7efcf7030, 0xc000359db0}) github.com/ollama/ollama/runner/ollamarunner/runner.go:453 +0x18c fp=0xc000195fb8 sp=0xc000195b58 pc=0x7ff7eebbd54c github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1() github.com/ollama/ollama/runner/ollamarunner/runner.go:1424 +0x28 fp=0xc000195fe0 sp=0xc000195fb8 pc=0x7ff7eebc6ca8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000195fe8 sp=0xc000195fe0 pc=0x7ff7ee58d9a1 created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/ollamarunner/runner.go:1424 +0x4c9 goroutine 42 gp=0xc0003f9180 m=nil [select]: runtime.gopark(0xc000047a08?, 0x2?, 0xc0?, 0x77?, 0xc00004786c?) runtime/proc.go:435 +0xce fp=0xc000047698 sp=0xc000047678 pc=0x7ff7ee58598e runtime.selectgo(0xc000047a08, 0xc000047868, 0xa7?, 0x0, 0x1?, 0x1) runtime/select.go:351 +0x837 fp=0xc0000477d0 sp=0xc000047698 pc=0x7ff7ee566437 github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc0001850e0, {0x7ff7efcf48c0, 0xc0003960e0}, 0xc0001a2280) github.com/ollama/ollama/runner/ollamarunner/runner.go:956 +0xc4e fp=0xc000047ac0 sp=0xc0000477d0 pc=0x7ff7eebc1d2e github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x7ff7efcf48c0?, 0xc0003960e0?}, 0xc000047b40?) <autogenerated>:1 +0x36 fp=0xc000047af0 sp=0xc000047ac0 pc=0x7ff7eebc7196 net/http.HandlerFunc.ServeHTTP(0xc0004ad500?, {0x7ff7efcf48c0?, 0xc0003960e0?}, 0xc000047b60?) net/http/server.go:2294 +0x29 fp=0xc000047b18 sp=0xc000047af0 pc=0x7ff7ee895ee9 net/http.(*ServeMux).ServeHTTP(0x7ff7ee52b785?, {0x7ff7efcf48c0, 0xc0003960e0}, 0xc0001a2280) net/http/server.go:2822 +0x1c4 fp=0xc000047b68 sp=0xc000047b18 pc=0x7ff7ee897de4 net/http.serverHandler.ServeHTTP({0x7ff7efcf0af0?}, {0x7ff7efcf48c0?, 0xc0003960e0?}, 0x1?) net/http/server.go:3301 +0x8e fp=0xc000047b98 sp=0xc000047b68 pc=0x7ff7ee8b586e net/http.(*conn).serve(0xc0006b0480, {0x7ff7efcf6ff8, 0xc0006ae9f0}) net/http/server.go:2102 +0x625 fp=0xc000047fb8 sp=0xc000047b98 pc=0x7ff7ee8943e5 net/http.(*Server).Serve.gowrap3() net/http/server.go:3454 +0x28 fp=0xc000047fe0 sp=0xc000047fb8 pc=0x7ff7ee899ca8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000047fe8 sp=0xc000047fe0 pc=0x7ff7ee58d9a1 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3454 +0x485 goroutine 2209 gp=0xc0005068c0 m=nil [IO wait]: runtime.gopark(0x0?, 0xc000689420?, 0xc8?, 0x94?, 0xc0006894cc?) runtime/proc.go:435 +0xce fp=0xc000e67d58 sp=0xc000e67d38 pc=0x7ff7ee58598e runtime.netpollblock(0x260?, 0xee520406?, 0xf7?) runtime/netpoll.go:575 +0xf7 fp=0xc000e67d90 sp=0xc000e67d58 pc=0x7ff7ee54bdf7 internal/poll.runtime_pollWait(0x14ed45c7c18, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc000e67db0 sp=0xc000e67d90 pc=0x7ff7ee584b25 internal/poll.(*pollDesc).wait(0x260?, 0x72?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000e67dd8 sp=0xc000e67db0 pc=0x7ff7ee61bf47 internal/poll.execIO(0xc000689420, 0x7ff7efb51a00) internal/poll/fd_windows.go:177 +0x105 fp=0xc000e67e50 sp=0xc000e67dd8 pc=0x7ff7ee61d3a5 internal/poll.(*FD).Read(0xc000689408, {0xc0006aeaf1, 0x1, 0x1}) internal/poll/fd_windows.go:438 +0x29b fp=0xc000e67ef0 sp=0xc000e67e50 pc=0x7ff7ee61e07b net.(*netFD).Read(0xc000689408, {0xc0006aeaf1?, 0xc0004b4d18?, 0xc000e67f70?}) net/fd_posix.go:55 +0x25 fp=0xc000e67f38 sp=0xc000e67ef0 pc=0x7ff7ee691465 net.(*conn).Read(0xc00007a7f0, {0xc0006aeaf1?, 0x0?, 0x7ff7efcfdc50?}) net/net.go:194 +0x45 fp=0xc000e67f80 sp=0xc000e67f38 pc=0x7ff7ee6a0b85 net/http.(*connReader).backgroundRead(0xc0006aeae0) net/http/server.go:690 +0x37 fp=0xc000e67fc8 sp=0xc000e67f80 pc=0x7ff7ee88e2b7 net/http.(*connReader).startBackgroundRead.gowrap2() net/http/server.go:686 +0x25 fp=0xc000e67fe0 sp=0xc000e67fc8 pc=0x7ff7ee88e1e5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000e67fe8 sp=0xc000e67fe0 pc=0x7ff7ee58d9a1 created by net/http.(*connReader).startBackgroundRead in goroutine 42 net/http/server.go:686 +0xb6 goroutine 1566 gp=0xc00090a8c0 m=nil [chan receive]: runtime.gopark(0x30?, 0x7ff7efa26ba0?, 0x1?, 0x9d?, 0xc000221b20?) runtime/proc.go:435 +0xce fp=0xc000221ad8 sp=0xc000221ab8 pc=0x7ff7ee58598e runtime.chanrecv(0xc000098310, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc000221b50 sp=0xc000221ad8 pc=0x7ff7ee522d45 runtime.chanrecv1(0x7ff7efb154d4?, 0x2c?) runtime/chan.go:506 +0x12 fp=0xc000221b78 sp=0xc000221b50 pc=0x7ff7ee5228d2 github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc0001850e0, {0x1, {0x7ff7efd036e0, 0xc0093cc040}, {0x7ff7efd134c8, 0xc000557dd0}, {0xc0019ce008, 0x1, 0x1}, {{0x7ff7efd134c8, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:645 +0x185 fp=0xc000221ef0 sp=0xc000221b78 pc=0x7ff7eebbf3a5 github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1() github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc000221fe0 sp=0xc000221ef0 pc=0x7ff7eebbd778 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000221fe8 sp=0xc000221fe0 pc=0x7ff7ee58d9a1 created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 41 github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd rax 0x0 rbx 0x0 rcx 0x154c24660e0 rdx 0x0 rdi 0x80 rsi 0x22e1060 rbp 0x154c2466080 rsp 0x133f0ff1f0 r8 0x22e1000 r9 0x0 r10 0x22e1060 r11 0x0 r12 0x0 r13 0x154bc411730 r14 0x0 r15 0x0 rip 0x7ffbceabbe7b rflags 0x10246 cs 0x33 fs 0x53 gs 0x2b time=2026-02-28T19:03:47.437+08:00 level=ERROR source=server.go:1610 msg="post predict" error="Post \"http://127.0.0.1:54447/completion\": read tcp 127.0.0.1:54453->127.0.0.1:54447: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2026/02/28 - 19:03:47 | 500 | 34.6100787s | 127.0.0.1 | POST "/api/chat" ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#55926
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?