github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 06:01:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #14530] when input with an image got 500 Internal Server Error: model runner has unexpectedly stopped, using qwen3.5 35b #55939

New Issue
Closed
opened 2026-04-29 09:58:30 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 09:58:30 -05:00
Owner
Copy Link

Originally created by @huanggou666 on GitHub (Mar 1, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14530

What is the issue?

Image

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @huanggou666 on GitHub (Mar 1, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14530 ### What is the issue? <img width="1146" height="772" alt="Image" src="https://github.com/user-attachments/assets/d379b8c9-bd91-4e4f-8fe0-71473be31e0d" /> ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-29 09:58:30 -05:00
GiteaMirror commented 2026-04-29 09:58:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 1, 2026):

Server logs will aid in debugging.

<!-- gh-comment-id:3979862222 --> @rick-github commented on GitHub (Mar 1, 2026): [Server logs](https://docs.ollama.com/troubleshooting) will aid in debugging.
GiteaMirror commented 2026-04-29 09:58:33 -05:00
Author
Owner
Copy Link

@huanggou666 commented on GitHub (Mar 1, 2026):

Server logs will aid in debugging.

time=2026-03-01T20:15:41.499+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:65536 OLLAMA_DEBUG:INFO OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\admin\\.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:false ROCR_VISIBLE_DEVICES:]"
time=2026-03-01T20:15:41.509+08:00 level=INFO source=routes.go:1665 msg="Ollama cloud disabled: false"
time=2026-03-01T20:15:41.521+08:00 level=INFO source=images.go:473 msg="total blobs: 7"
time=2026-03-01T20:15:41.522+08:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0"
time=2026-03-01T20:15:41.524+08:00 level=INFO source=routes.go:1718 msg="Listening on 127.0.0.1:11434 (version 0.17.1)"
time=2026-03-01T20:15:41.526+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-03-01T20:15:41.563+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53165"
time=2026-03-01T20:15:41.995+08:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled.  To enable, set OLLAMA_VULKAN=1"
time=2026-03-01T20:15:41.996+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53171"
time=2026-03-01T20:15:43.739+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53179"
time=2026-03-01T20:15:44.255+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53187"
time=2026-03-01T20:15:44.390+08:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 filter_id="" library=CUDA compute=8.9 name=CUDA0 description="NVIDIA GeForce RTX 4090" libdirs=ollama,cuda_v12 driver=12.3 pci_id=0000:01:00.0 type=discrete total="24.0 GiB" available="7.3 GiB"
time=2026-03-01T20:15:44.390+08:00 level=INFO source=routes.go:1768 msg="vram-based default context" total_vram="24.0 GiB" default_num_ctx=32768
[GIN] 2026/03/01 - 20:15:44 | 200 |      2.7594ms |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/03/01 - 20:15:44 | 200 |      2.7594ms |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/03/01 - 20:15:44 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/03/01 - 20:15:44 | 200 |     14.0181ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:15:44 | 200 |     139.058ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/03/01 - 20:15:45 | 200 |    850.7359ms |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/03/01 - 20:15:45 | 200 |    848.0295ms |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/03/01 - 20:16:00 | 200 |      1.5793ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:16:00 | 200 |    103.7148ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/03/01 - 20:16:00 | 200 |     98.8908ms |       127.0.0.1 | POST     "/api/show"
time=2026-03-01T20:16:00.871+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 58309"
time=2026-03-01T20:16:01.037+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-03-01T20:16:01.037+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2026-03-01T20:16:01.037+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32
time=2026-03-01T20:16:01.105+08:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-03-01T20:16:01.107+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\admin\\.ollama\\models\\blobs\\sha256-10aa4f639021bf57bee8f43057539343d6d62c79ee0b67c1f24f2c07cea81795 --port 58315"
time=2026-03-01T20:16:01.108+08:00 level=INFO source=sched.go:491 msg="system memory" total="63.8 GiB" free="33.7 GiB" free_swap="58.0 GiB"
time=2026-03-01T20:16:01.108+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 library=CUDA available="6.8 GiB" free="7.3 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-03-01T20:16:01.108+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=65 requested=-1
time=2026-03-01T20:16:01.140+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
time=2026-03-01T20:16:01.150+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:58315"
time=2026-03-01T20:16:01.152+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:65[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:65(0..64)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:16:01.179+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35 file_type=Q4_K_M name="" description="" num_tensors=1307 num_key_values=53
load_backend: loaded CPU backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-782b5f56-fe71-6c9e-7d60-663269fc0762
load_backend: loaded CUDA backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2026-03-01T20:16:01.253+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 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-03-01T20:16:02.305+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:16[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:16(48..63)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:16:02.849+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:16[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:16(48..63)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:16:04.500+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:16[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:16(48..63)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.4 GiB"
time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="12.8 GiB"
time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="1.9 GiB"
time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="5.7 GiB"
time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.4 GiB"
time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="1.0 GiB"
time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:272 msg="total memory" size="26.3 GiB"
time=2026-03-01T20:16:04.501+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1
time=2026-03-01T20:16:04.501+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
time=2026-03-01T20:16:04.500+08:00 level=INFO source=ggml.go:482 msg="offloading 16 repeating layers to GPU"
time=2026-03-01T20:16:04.501+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
time=2026-03-01T20:16:04.501+08:00 level=INFO source=ggml.go:494 msg="offloaded 16/65 layers to GPU"
time=2026-03-01T20:16:04.501+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model"
time=2026-03-01T20:16:12.785+08:00 level=INFO source=server.go:1388 msg="llama runner started in 11.68 seconds"
[GIN] 2026/03/01 - 20:16:30 | 200 |      1.5477ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:16:31 | 200 |   30.7550542s |       127.0.0.1 | POST     "/api/chat"
ggml_backend_cuda_device_get_memory device GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 utilizing NVML memory reporting free: 536498176 total: 25757220864
time=2026-03-01T20:16:33.022+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 58447"
[GIN] 2026/03/01 - 20:16:33 | 200 |    132.2362ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/03/01 - 20:16:37 | 200 |      1.5603ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:16:39 | 200 |      1.5525ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:16:39 | 200 |    112.6558ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/03/01 - 20:16:39 | 200 |    107.6341ms |       127.0.0.1 | POST     "/api/show"
time=2026-03-01T20:16:39.824+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56195"
time=2026-03-01T20:16:39.995+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-03-01T20:16:39.995+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2026-03-01T20:16:39.995+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32
time=2026-03-01T20:16:40.071+08:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-03-01T20:16:40.072+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\admin\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 56201"
time=2026-03-01T20:16:40.076+08:00 level=INFO source=sched.go:491 msg="system memory" total="63.8 GiB" free="33.3 GiB" free_swap="58.0 GiB"
time=2026-03-01T20:16:40.076+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 library=CUDA available="7.5 GiB" free="8.0 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-03-01T20:16:40.076+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1
time=2026-03-01T20:16:40.107+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
time=2026-03-01T20:16:40.119+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:56201"
time=2026-03-01T20:16:40.129+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:41[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:16:40.159+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\admin\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-782b5f56-fe71-6c9e-7d60-663269fc0762
load_backend: loaded CUDA backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2026-03-01T20:16:40.253+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 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-03-01T20:16:41.080+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:16:41.617+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=ggml.go:482 msg="offloading 11 repeating layers to GPU"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=ggml.go:494 msg="offloaded 11/41 layers to GPU"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="5.6 GiB"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="16.6 GiB"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="802.8 MiB"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="2.0 GiB"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.2 GiB"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="630.8 MiB"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:272 msg="total memory" size="26.8 GiB"
time=2026-03-01T20:16:42.639+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1
time=2026-03-01T20:16:42.639+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
time=2026-03-01T20:16:42.640+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model"
time=2026-03-01T20:16:50.671+08:00 level=INFO source=server.go:1388 msg="llama runner started in 10.59 seconds"
[GIN] 2026/03/01 - 20:17:09 | 200 |       2.148ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:17:22 | 200 |   42.5667241s |       127.0.0.1 | POST     "/api/chat"
ggml_backend_cuda_device_get_memory device GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 utilizing NVML memory reporting free: 465629184 total: 25757220864
time=2026-03-01T20:17:23.480+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53305"
[GIN] 2026/03/01 - 20:17:39 | 200 |      1.0241ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:17:59 | 200 |    108.3472ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/03/01 - 20:17:59 | 200 |    100.6351ms |       127.0.0.1 | POST     "/api/show"
time=2026-03-01T20:17:59.516+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60623"
time=2026-03-01T20:17:59.673+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-03-01T20:17:59.673+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2026-03-01T20:17:59.673+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32
time=2026-03-01T20:17:59.743+08:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-03-01T20:17:59.744+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\admin\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 60629"
time=2026-03-01T20:17:59.747+08:00 level=INFO source=sched.go:491 msg="system memory" total="63.8 GiB" free="32.6 GiB" free_swap="57.5 GiB"
time=2026-03-01T20:17:59.747+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 library=CUDA available="7.7 GiB" free="8.1 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-03-01T20:17:59.747+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1
time=2026-03-01T20:17:59.778+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
time=2026-03-01T20:17:59.789+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:60629"
time=2026-03-01T20:17:59.790+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:41[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:17:59.818+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\admin\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-782b5f56-fe71-6c9e-7d60-663269fc0762
load_backend: loaded CUDA backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2026-03-01T20:17:59.896+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 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-03-01T20:18:00.611+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:18:01.083+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=ggml.go:482 msg="offloading 11 repeating layers to GPU"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=ggml.go:494 msg="offloaded 11/41 layers to GPU"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="5.6 GiB"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="16.6 GiB"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="802.8 MiB"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="2.0 GiB"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.2 GiB"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="630.8 MiB"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:272 msg="total memory" size="26.8 GiB"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1
time=2026-03-01T20:18:02.005+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
time=2026-03-01T20:18:02.005+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model"
[GIN] 2026/03/01 - 20:18:09 | 200 |      10.516ms |       127.0.0.1 | GET      "/api/tags"
time=2026-03-01T20:18:11.794+08:00 level=INFO source=server.go:1388 msg="llama runner started in 12.05 seconds"
CUDA error: invalid argument
  current device: 0, in function ggml_cuda_cpy at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:438
  cudaMemcpyAsyncReserve(src1_ddc, src0_ddc, ggml_nbytes(src0), cudaMemcpyDeviceToDevice, main_stream)
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:94: CUDA error
time=2026-03-01T20:18:12.705+08:00 level=ERROR source=server.go:1610 msg="post predict" error="Post \"http://127.0.0.1:60629/completion\": read tcp 127.0.0.1:60634->127.0.0.1:60629: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2026/03/01 - 20:18:12 | 500 |   13.2851628s |       127.0.0.1 | POST     "/api/chat"
time=2026-03-01T20:18:13.767+08:00 level=ERROR source=server.go:304 msg="llama runner terminated" error="exit status 1"
time=2026-03-01T20:18:13.777+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60749"
time=2026-03-01T20:18:14.221+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60757"
time=2026-03-01T20:18:14.471+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60763"
time=2026-03-01T20:18:14.720+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60769"
time=2026-03-01T20:18:14.970+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60775"
time=2026-03-01T20:18:15.221+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60781"
time=2026-03-01T20:18:15.472+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60787"
time=2026-03-01T20:18:15.720+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60793"
time=2026-03-01T20:18:15.970+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60799"
time=2026-03-01T20:18:16.220+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60805"
time=2026-03-01T20:18:16.471+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60811"
time=2026-03-01T20:18:16.721+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60817"
time=2026-03-01T20:18:16.971+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60823"
time=2026-03-01T20:18:17.220+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60829"
time=2026-03-01T20:18:17.470+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60835"
time=2026-03-01T20:18:17.720+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60841"
time=2026-03-01T20:18:17.971+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60847"
time=2026-03-01T20:18:18.221+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60853"
time=2026-03-01T20:18:18.470+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60860"
time=2026-03-01T20:18:18.720+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60866"
time=2026-03-01T20:18:18.972+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60872"
time=2026-03-01T20:18:18.974+08:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout"
time=2026-03-01T20:18:18.974+08:00 level=WARN source=runner.go:356 msg="unable to refresh free memory, using old values"
[GIN] 2026/03/01 - 20:18:39 | 200 |       1.024ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:19:09 | 200 |      1.0222ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:19:39 | 200 |      1.5053ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:19:48 | 200 |       1.021ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:19:54 | 200 |      1.5542ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:19:54 | 200 |    107.0934ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/03/01 - 20:19:55 | 200 |     99.8748ms |       127.0.0.1 | POST     "/api/show"
time=2026-03-01T20:19:55.125+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 59688"
time=2026-03-01T20:19:55.287+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-03-01T20:19:55.288+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2026-03-01T20:19:55.288+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32
time=2026-03-01T20:19:55.357+08:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-03-01T20:19:55.359+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\admin\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 59694"
time=2026-03-01T20:19:55.360+08:00 level=INFO source=sched.go:491 msg="system memory" total="63.8 GiB" free="31.9 GiB" free_swap="57.3 GiB"
time=2026-03-01T20:19:55.360+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 library=CUDA available="8.2 GiB" free="8.6 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-03-01T20:19:55.360+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1
time=2026-03-01T20:19:55.392+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
time=2026-03-01T20:19:55.402+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:59694"
time=2026-03-01T20:19:55.403+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:41[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:19:55.432+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\admin\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-782b5f56-fe71-6c9e-7d60-663269fc0762
load_backend: loaded CUDA backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2026-03-01T20:19:55.511+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 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-03-01T20:19:56.260+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:19:56.774+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="6.1 GiB"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="16.1 GiB"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="855.1 MiB"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="1.9 GiB"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.2 GiB"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="630.8 MiB"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:272 msg="total memory" size="26.8 GiB"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1
time=2026-03-01T20:19:57.716+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=ggml.go:482 msg="offloading 12 repeating layers to GPU"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=ggml.go:494 msg="offloaded 12/41 layers to GPU"
time=2026-03-01T20:19:57.716+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model"
time=2026-03-01T20:20:05.996+08:00 level=INFO source=server.go:1388 msg="llama runner started in 10.64 seconds"
[GIN] 2026/03/01 - 20:20:24 | 200 |      1.5423ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:20:26 | 200 |   31.0344526s |       127.0.0.1 | POST     "/api/chat"
ggml_backend_cuda_device_get_memory device GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 utilizing NVML memory reporting free: 507703296 total: 25757220864
time=2026-03-01T20:20:27.256+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62707"
[GIN] 2026/03/01 - 20:20:54 | 200 |      1.0281ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:21:02 | 200 |    104.3437ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/03/01 - 20:21:02 | 200 |    103.3697ms |       127.0.0.1 | POST     "/api/show"
time=2026-03-01T20:21:02.792+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62743"
time=2026-03-01T20:21:02.977+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-03-01T20:21:02.977+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2026-03-01T20:21:02.977+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32
time=2026-03-01T20:21:03.046+08:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-03-01T20:21:03.046+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\admin\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 62749"
time=2026-03-01T20:21:03.048+08:00 level=INFO source=sched.go:491 msg="system memory" total="63.8 GiB" free="31.3 GiB" free_swap="57.2 GiB"
time=2026-03-01T20:21:03.048+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 library=CUDA available="8.5 GiB" free="8.9 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-03-01T20:21:03.048+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1
time=2026-03-01T20:21:03.080+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
time=2026-03-01T20:21:03.090+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:62749"
time=2026-03-01T20:21:03.092+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:41[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:21:03.119+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\admin\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-782b5f56-fe71-6c9e-7d60-663269fc0762
load_backend: loaded CUDA backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2026-03-01T20:21:03.202+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 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-03-01T20:21:03.984+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:21:04.501+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=ggml.go:482 msg="offloading 12 repeating layers to GPU"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=ggml.go:494 msg="offloaded 12/41 layers to GPU"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="6.1 GiB"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="16.1 GiB"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="855.1 MiB"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="1.9 GiB"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.2 GiB"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="630.8 MiB"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:272 msg="total memory" size="26.8 GiB"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1
time=2026-03-01T20:21:05.443+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
time=2026-03-01T20:21:05.443+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model"
time=2026-03-01T20:21:13.978+08:00 level=INFO source=server.go:1388 msg="llama runner started in 10.93 seconds"
CUDA error: invalid argument
  current device: 0, in function ggml_cuda_cpy at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:438
  cudaMemcpyAsyncReserve(src1_ddc, src0_ddc, ggml_nbytes(src0), cudaMemcpyDeviceToDevice, main_stream)
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:94: CUDA error
time=2026-03-01T20:21:14.842+08:00 level=ERROR source=server.go:1610 msg="post predict" error="Post \"http://127.0.0.1:62749/completion\": read tcp 127.0.0.1:62754->127.0.0.1:62749: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2026/03/01 - 20:21:14 | 500 |   12.1471841s |       127.0.0.1 | POST     "/api/chat"
time=2026-03-01T20:21:16.247+08:00 level=ERROR source=server.go:304 msg="llama runner terminated" error="exit status 1"
time=2026-03-01T20:21:16.256+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62904"
time=2026-03-01T20:21:16.735+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62913"
time=2026-03-01T20:21:16.985+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62919"
time=2026-03-01T20:21:17.235+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62925"
time=2026-03-01T20:21:17.485+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62932"
time=2026-03-01T20:21:17.735+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62938"
time=2026-03-01T20:21:17.985+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62944"
time=2026-03-01T20:21:18.235+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62950"
time=2026-03-01T20:21:18.485+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62956"
time=2026-03-01T20:21:18.735+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62962"
time=2026-03-01T20:21:18.985+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62968"
time=2026-03-01T20:21:19.235+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62974"
time=2026-03-01T20:21:19.485+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62980"
time=2026-03-01T20:21:19.735+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62986"
time=2026-03-01T20:21:19.985+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62992"
time=2026-03-01T20:21:20.235+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62997"
time=2026-03-01T20:21:20.485+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 63003"
time=2026-03-01T20:21:20.735+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 63009"
time=2026-03-01T20:21:20.985+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 63015"
time=2026-03-01T20:21:21.234+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 63021"
time=2026-03-01T20:21:21.486+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 63026"
time=2026-03-01T20:21:21.488+08:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout"
time=2026-03-01T20:21:21.488+08:00 level=WARN source=runner.go:356 msg="unable to refresh free memory, using old values"
[GIN] 2026/03/01 - 20:21:24 | 200 |      1.6338ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:21:54 | 200 |      1.0203ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:22:25 | 200 |      2.7105ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:22:26 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/03/01 - 20:22:26 | 200 |      3.3934ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:22:27 | 200 |    1.2263661s |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/03/01 - 20:22:57 | 200 |      1.2288ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:23:28 | 200 |      1.5551ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:23:59 | 200 |      1.0272ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:24:30 | 200 |      2.0291ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:25:01 | 200 |      1.0238ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:25:32 | 200 |      1.7096ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:26:03 | 200 |      1.0602ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:26:34 | 200 |      1.0217ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:26:35 | 200 |         504µs |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/03/01 - 20:26:35 | 200 |      1.0821ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:27:05 | 200 |      1.0231ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:27:35 | 200 |      2.0757ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:28:05 | 200 |      1.0982ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/01 - 20:28:35 | 200 |      1.0164ms |       127.0.0.1 | GET      "/api/tags"
<!-- gh-comment-id:3979869315 --> @huanggou666 commented on GitHub (Mar 1, 2026): > [Server logs](https://docs.ollama.com/troubleshooting) will aid in debugging. ``` time=2026-03-01T20:15:41.499+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:65536 OLLAMA_DEBUG:INFO OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\admin\\.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:false ROCR_VISIBLE_DEVICES:]" time=2026-03-01T20:15:41.509+08:00 level=INFO source=routes.go:1665 msg="Ollama cloud disabled: false" time=2026-03-01T20:15:41.521+08:00 level=INFO source=images.go:473 msg="total blobs: 7" time=2026-03-01T20:15:41.522+08:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0" time=2026-03-01T20:15:41.524+08:00 level=INFO source=routes.go:1718 msg="Listening on 127.0.0.1:11434 (version 0.17.1)" time=2026-03-01T20:15:41.526+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2026-03-01T20:15:41.563+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53165" time=2026-03-01T20:15:41.995+08:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" time=2026-03-01T20:15:41.996+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53171" time=2026-03-01T20:15:43.739+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53179" time=2026-03-01T20:15:44.255+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53187" time=2026-03-01T20:15:44.390+08:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 filter_id="" library=CUDA compute=8.9 name=CUDA0 description="NVIDIA GeForce RTX 4090" libdirs=ollama,cuda_v12 driver=12.3 pci_id=0000:01:00.0 type=discrete total="24.0 GiB" available="7.3 GiB" time=2026-03-01T20:15:44.390+08:00 level=INFO source=routes.go:1768 msg="vram-based default context" total_vram="24.0 GiB" default_num_ctx=32768 [GIN] 2026/03/01 - 20:15:44 | 200 | 2.7594ms | 127.0.0.1 | GET "/api/version" [GIN] 2026/03/01 - 20:15:44 | 200 | 2.7594ms | 127.0.0.1 | GET "/api/version" [GIN] 2026/03/01 - 20:15:44 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2026/03/01 - 20:15:44 | 200 | 14.0181ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:15:44 | 200 | 139.058ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/03/01 - 20:15:45 | 200 | 850.7359ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/03/01 - 20:15:45 | 200 | 848.0295ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/03/01 - 20:16:00 | 200 | 1.5793ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:16:00 | 200 | 103.7148ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/03/01 - 20:16:00 | 200 | 98.8908ms | 127.0.0.1 | POST "/api/show" time=2026-03-01T20:16:00.871+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 58309" time=2026-03-01T20:16:01.037+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-03-01T20:16:01.037+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2026-03-01T20:16:01.037+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32 time=2026-03-01T20:16:01.105+08:00 level=INFO source=server.go:247 msg="enabling flash attention" time=2026-03-01T20:16:01.107+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\admin\\.ollama\\models\\blobs\\sha256-10aa4f639021bf57bee8f43057539343d6d62c79ee0b67c1f24f2c07cea81795 --port 58315" time=2026-03-01T20:16:01.108+08:00 level=INFO source=sched.go:491 msg="system memory" total="63.8 GiB" free="33.7 GiB" free_swap="58.0 GiB" time=2026-03-01T20:16:01.108+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 library=CUDA available="6.8 GiB" free="7.3 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-03-01T20:16:01.108+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=65 requested=-1 time=2026-03-01T20:16:01.140+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine" time=2026-03-01T20:16:01.150+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:58315" time=2026-03-01T20:16:01.152+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:65[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:65(0..64)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:16:01.179+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35 file_type=Q4_K_M name="" description="" num_tensors=1307 num_key_values=53 load_backend: loaded CPU backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 load_backend: loaded CUDA backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2026-03-01T20:16:01.253+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 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-03-01T20:16:02.305+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:16[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:16(48..63)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:16:02.849+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:16[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:16(48..63)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:16:04.500+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:16[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:16(48..63)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.4 GiB" time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="12.8 GiB" time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="1.9 GiB" time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="5.7 GiB" time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.4 GiB" time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="1.0 GiB" time=2026-03-01T20:16:04.501+08:00 level=INFO source=device.go:272 msg="total memory" size="26.3 GiB" time=2026-03-01T20:16:04.501+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1 time=2026-03-01T20:16:04.501+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding" time=2026-03-01T20:16:04.500+08:00 level=INFO source=ggml.go:482 msg="offloading 16 repeating layers to GPU" time=2026-03-01T20:16:04.501+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU" time=2026-03-01T20:16:04.501+08:00 level=INFO source=ggml.go:494 msg="offloaded 16/65 layers to GPU" time=2026-03-01T20:16:04.501+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model" time=2026-03-01T20:16:12.785+08:00 level=INFO source=server.go:1388 msg="llama runner started in 11.68 seconds" [GIN] 2026/03/01 - 20:16:30 | 200 | 1.5477ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:16:31 | 200 | 30.7550542s | 127.0.0.1 | POST "/api/chat" ggml_backend_cuda_device_get_memory device GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 utilizing NVML memory reporting free: 536498176 total: 25757220864 time=2026-03-01T20:16:33.022+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 58447" [GIN] 2026/03/01 - 20:16:33 | 200 | 132.2362ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/03/01 - 20:16:37 | 200 | 1.5603ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:16:39 | 200 | 1.5525ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:16:39 | 200 | 112.6558ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/03/01 - 20:16:39 | 200 | 107.6341ms | 127.0.0.1 | POST "/api/show" time=2026-03-01T20:16:39.824+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56195" time=2026-03-01T20:16:39.995+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-03-01T20:16:39.995+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2026-03-01T20:16:39.995+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32 time=2026-03-01T20:16:40.071+08:00 level=INFO source=server.go:247 msg="enabling flash attention" time=2026-03-01T20:16:40.072+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\admin\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 56201" time=2026-03-01T20:16:40.076+08:00 level=INFO source=sched.go:491 msg="system memory" total="63.8 GiB" free="33.3 GiB" free_swap="58.0 GiB" time=2026-03-01T20:16:40.076+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 library=CUDA available="7.5 GiB" free="8.0 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-03-01T20:16:40.076+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1 time=2026-03-01T20:16:40.107+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine" time=2026-03-01T20:16:40.119+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:56201" time=2026-03-01T20:16:40.129+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:41[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:16:40.159+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\admin\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 load_backend: loaded CUDA backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2026-03-01T20:16:40.253+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 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-03-01T20:16:41.080+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:16:41.617+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:16:42.639+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:16:42.639+08:00 level=INFO source=ggml.go:482 msg="offloading 11 repeating layers to GPU" time=2026-03-01T20:16:42.639+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU" time=2026-03-01T20:16:42.639+08:00 level=INFO source=ggml.go:494 msg="offloaded 11/41 layers to GPU" time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="5.6 GiB" time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="16.6 GiB" time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="802.8 MiB" time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="2.0 GiB" time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.2 GiB" time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="630.8 MiB" time=2026-03-01T20:16:42.639+08:00 level=INFO source=device.go:272 msg="total memory" size="26.8 GiB" time=2026-03-01T20:16:42.639+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1 time=2026-03-01T20:16:42.639+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding" time=2026-03-01T20:16:42.640+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model" time=2026-03-01T20:16:50.671+08:00 level=INFO source=server.go:1388 msg="llama runner started in 10.59 seconds" [GIN] 2026/03/01 - 20:17:09 | 200 | 2.148ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:17:22 | 200 | 42.5667241s | 127.0.0.1 | POST "/api/chat" ggml_backend_cuda_device_get_memory device GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 utilizing NVML memory reporting free: 465629184 total: 25757220864 time=2026-03-01T20:17:23.480+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53305" [GIN] 2026/03/01 - 20:17:39 | 200 | 1.0241ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:17:59 | 200 | 108.3472ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/03/01 - 20:17:59 | 200 | 100.6351ms | 127.0.0.1 | POST "/api/show" time=2026-03-01T20:17:59.516+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60623" time=2026-03-01T20:17:59.673+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-03-01T20:17:59.673+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2026-03-01T20:17:59.673+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32 time=2026-03-01T20:17:59.743+08:00 level=INFO source=server.go:247 msg="enabling flash attention" time=2026-03-01T20:17:59.744+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\admin\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 60629" time=2026-03-01T20:17:59.747+08:00 level=INFO source=sched.go:491 msg="system memory" total="63.8 GiB" free="32.6 GiB" free_swap="57.5 GiB" time=2026-03-01T20:17:59.747+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 library=CUDA available="7.7 GiB" free="8.1 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-03-01T20:17:59.747+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1 time=2026-03-01T20:17:59.778+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine" time=2026-03-01T20:17:59.789+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:60629" time=2026-03-01T20:17:59.790+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:41[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:17:59.818+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\admin\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 load_backend: loaded CUDA backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2026-03-01T20:17:59.896+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 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-03-01T20:18:00.611+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:18:01.083+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:18:02.005+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:11[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:11(29..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:18:02.005+08:00 level=INFO source=ggml.go:482 msg="offloading 11 repeating layers to GPU" time=2026-03-01T20:18:02.005+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU" time=2026-03-01T20:18:02.005+08:00 level=INFO source=ggml.go:494 msg="offloaded 11/41 layers to GPU" time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="5.6 GiB" time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="16.6 GiB" time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="802.8 MiB" time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="2.0 GiB" time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.2 GiB" time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="630.8 MiB" time=2026-03-01T20:18:02.005+08:00 level=INFO source=device.go:272 msg="total memory" size="26.8 GiB" time=2026-03-01T20:18:02.005+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1 time=2026-03-01T20:18:02.005+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding" time=2026-03-01T20:18:02.005+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model" [GIN] 2026/03/01 - 20:18:09 | 200 | 10.516ms | 127.0.0.1 | GET "/api/tags" time=2026-03-01T20:18:11.794+08:00 level=INFO source=server.go:1388 msg="llama runner started in 12.05 seconds" CUDA error: invalid argument current device: 0, in function ggml_cuda_cpy at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:438 cudaMemcpyAsyncReserve(src1_ddc, src0_ddc, ggml_nbytes(src0), cudaMemcpyDeviceToDevice, main_stream) C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:94: CUDA error time=2026-03-01T20:18:12.705+08:00 level=ERROR source=server.go:1610 msg="post predict" error="Post \"http://127.0.0.1:60629/completion\": read tcp 127.0.0.1:60634->127.0.0.1:60629: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2026/03/01 - 20:18:12 | 500 | 13.2851628s | 127.0.0.1 | POST "/api/chat" time=2026-03-01T20:18:13.767+08:00 level=ERROR source=server.go:304 msg="llama runner terminated" error="exit status 1" time=2026-03-01T20:18:13.777+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60749" time=2026-03-01T20:18:14.221+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60757" time=2026-03-01T20:18:14.471+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60763" time=2026-03-01T20:18:14.720+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60769" time=2026-03-01T20:18:14.970+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60775" time=2026-03-01T20:18:15.221+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60781" time=2026-03-01T20:18:15.472+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60787" time=2026-03-01T20:18:15.720+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60793" time=2026-03-01T20:18:15.970+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60799" time=2026-03-01T20:18:16.220+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60805" time=2026-03-01T20:18:16.471+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60811" time=2026-03-01T20:18:16.721+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60817" time=2026-03-01T20:18:16.971+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60823" time=2026-03-01T20:18:17.220+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60829" time=2026-03-01T20:18:17.470+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60835" time=2026-03-01T20:18:17.720+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60841" time=2026-03-01T20:18:17.971+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60847" time=2026-03-01T20:18:18.221+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60853" time=2026-03-01T20:18:18.470+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60860" time=2026-03-01T20:18:18.720+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60866" time=2026-03-01T20:18:18.972+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 60872" time=2026-03-01T20:18:18.974+08:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout" time=2026-03-01T20:18:18.974+08:00 level=WARN source=runner.go:356 msg="unable to refresh free memory, using old values" [GIN] 2026/03/01 - 20:18:39 | 200 | 1.024ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:19:09 | 200 | 1.0222ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:19:39 | 200 | 1.5053ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:19:48 | 200 | 1.021ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:19:54 | 200 | 1.5542ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:19:54 | 200 | 107.0934ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/03/01 - 20:19:55 | 200 | 99.8748ms | 127.0.0.1 | POST "/api/show" time=2026-03-01T20:19:55.125+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 59688" time=2026-03-01T20:19:55.287+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-03-01T20:19:55.288+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2026-03-01T20:19:55.288+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32 time=2026-03-01T20:19:55.357+08:00 level=INFO source=server.go:247 msg="enabling flash attention" time=2026-03-01T20:19:55.359+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\admin\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 59694" time=2026-03-01T20:19:55.360+08:00 level=INFO source=sched.go:491 msg="system memory" total="63.8 GiB" free="31.9 GiB" free_swap="57.3 GiB" time=2026-03-01T20:19:55.360+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 library=CUDA available="8.2 GiB" free="8.6 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-03-01T20:19:55.360+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1 time=2026-03-01T20:19:55.392+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine" time=2026-03-01T20:19:55.402+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:59694" time=2026-03-01T20:19:55.403+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:41[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:19:55.432+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\admin\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 load_backend: loaded CUDA backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2026-03-01T20:19:55.511+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 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-03-01T20:19:56.260+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:19:56.774+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="6.1 GiB" time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="16.1 GiB" time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="855.1 MiB" time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="1.9 GiB" time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.2 GiB" time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="630.8 MiB" time=2026-03-01T20:19:57.716+08:00 level=INFO source=device.go:272 msg="total memory" size="26.8 GiB" time=2026-03-01T20:19:57.716+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1 time=2026-03-01T20:19:57.716+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:19:57.716+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding" time=2026-03-01T20:19:57.716+08:00 level=INFO source=ggml.go:482 msg="offloading 12 repeating layers to GPU" time=2026-03-01T20:19:57.716+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU" time=2026-03-01T20:19:57.716+08:00 level=INFO source=ggml.go:494 msg="offloaded 12/41 layers to GPU" time=2026-03-01T20:19:57.716+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model" time=2026-03-01T20:20:05.996+08:00 level=INFO source=server.go:1388 msg="llama runner started in 10.64 seconds" [GIN] 2026/03/01 - 20:20:24 | 200 | 1.5423ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:20:26 | 200 | 31.0344526s | 127.0.0.1 | POST "/api/chat" ggml_backend_cuda_device_get_memory device GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 utilizing NVML memory reporting free: 507703296 total: 25757220864 time=2026-03-01T20:20:27.256+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62707" [GIN] 2026/03/01 - 20:20:54 | 200 | 1.0281ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:21:02 | 200 | 104.3437ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/03/01 - 20:21:02 | 200 | 103.3697ms | 127.0.0.1 | POST "/api/show" time=2026-03-01T20:21:02.792+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62743" time=2026-03-01T20:21:02.977+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-03-01T20:21:02.977+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2026-03-01T20:21:02.977+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=32 time=2026-03-01T20:21:03.046+08:00 level=INFO source=server.go:247 msg="enabling flash attention" time=2026-03-01T20:21:03.046+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\admin\\.ollama\\models\\blobs\\sha256-2abd0d805943fa113f934d1ae4f2d5a749b5d4fe2a0a9c64b645c1df15868da7 --port 62749" time=2026-03-01T20:21:03.048+08:00 level=INFO source=sched.go:491 msg="system memory" total="63.8 GiB" free="31.3 GiB" free_swap="57.2 GiB" time=2026-03-01T20:21:03.048+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 library=CUDA available="8.5 GiB" free="8.9 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-03-01T20:21:03.048+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=41 requested=-1 time=2026-03-01T20:21:03.080+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine" time=2026-03-01T20:21:03.090+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:62749" time=2026-03-01T20:21:03.092+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:41[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:41(0..40)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:21:03.119+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\admin\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 load_backend: loaded CUDA backend from C:\Users\admin\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2026-03-01T20:21:03.202+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 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-03-01T20:21:03.984+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:21:04.501+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:21:05.443+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:8 GPULayers:12[ID:GPU-782b5f56-fe71-6c9e-7d60-663269fc0762 Layers:12(28..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-01T20:21:05.443+08:00 level=INFO source=ggml.go:482 msg="offloading 12 repeating layers to GPU" time=2026-03-01T20:21:05.443+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU" time=2026-03-01T20:21:05.443+08:00 level=INFO source=ggml.go:494 msg="offloaded 12/41 layers to GPU" time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="6.1 GiB" time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="16.1 GiB" time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="855.1 MiB" time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="1.9 GiB" time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="1.2 GiB" time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="630.8 MiB" time=2026-03-01T20:21:05.443+08:00 level=INFO source=device.go:272 msg="total memory" size="26.8 GiB" time=2026-03-01T20:21:05.443+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1 time=2026-03-01T20:21:05.443+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding" time=2026-03-01T20:21:05.443+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model" time=2026-03-01T20:21:13.978+08:00 level=INFO source=server.go:1388 msg="llama runner started in 10.93 seconds" CUDA error: invalid argument current device: 0, in function ggml_cuda_cpy at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:438 cudaMemcpyAsyncReserve(src1_ddc, src0_ddc, ggml_nbytes(src0), cudaMemcpyDeviceToDevice, main_stream) C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:94: CUDA error time=2026-03-01T20:21:14.842+08:00 level=ERROR source=server.go:1610 msg="post predict" error="Post \"http://127.0.0.1:62749/completion\": read tcp 127.0.0.1:62754->127.0.0.1:62749: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2026/03/01 - 20:21:14 | 500 | 12.1471841s | 127.0.0.1 | POST "/api/chat" time=2026-03-01T20:21:16.247+08:00 level=ERROR source=server.go:304 msg="llama runner terminated" error="exit status 1" time=2026-03-01T20:21:16.256+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62904" time=2026-03-01T20:21:16.735+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62913" time=2026-03-01T20:21:16.985+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62919" time=2026-03-01T20:21:17.235+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62925" time=2026-03-01T20:21:17.485+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62932" time=2026-03-01T20:21:17.735+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62938" time=2026-03-01T20:21:17.985+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62944" time=2026-03-01T20:21:18.235+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62950" time=2026-03-01T20:21:18.485+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62956" time=2026-03-01T20:21:18.735+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62962" time=2026-03-01T20:21:18.985+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62968" time=2026-03-01T20:21:19.235+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62974" time=2026-03-01T20:21:19.485+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62980" time=2026-03-01T20:21:19.735+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62986" time=2026-03-01T20:21:19.985+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62992" time=2026-03-01T20:21:20.235+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 62997" time=2026-03-01T20:21:20.485+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 63003" time=2026-03-01T20:21:20.735+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 63009" time=2026-03-01T20:21:20.985+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 63015" time=2026-03-01T20:21:21.234+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 63021" time=2026-03-01T20:21:21.486+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 63026" time=2026-03-01T20:21:21.488+08:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\admin\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout" time=2026-03-01T20:21:21.488+08:00 level=WARN source=runner.go:356 msg="unable to refresh free memory, using old values" [GIN] 2026/03/01 - 20:21:24 | 200 | 1.6338ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:21:54 | 200 | 1.0203ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:22:25 | 200 | 2.7105ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:22:26 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2026/03/01 - 20:22:26 | 200 | 3.3934ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:22:27 | 200 | 1.2263661s | 127.0.0.1 | POST "/api/me" [GIN] 2026/03/01 - 20:22:57 | 200 | 1.2288ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:23:28 | 200 | 1.5551ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:23:59 | 200 | 1.0272ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:24:30 | 200 | 2.0291ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:25:01 | 200 | 1.0238ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:25:32 | 200 | 1.7096ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:26:03 | 200 | 1.0602ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:26:34 | 200 | 1.0217ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:26:35 | 200 | 504µs | 127.0.0.1 | GET "/api/version" [GIN] 2026/03/01 - 20:26:35 | 200 | 1.0821ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:27:05 | 200 | 1.0231ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:27:35 | 200 | 2.0757ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:28:05 | 200 | 1.0982ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/01 - 20:28:35 | 200 | 1.0164ms | 127.0.0.1 | GET "/api/tags" ```
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#55939
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?