[GH-ISSUE #13585] 0.13.5 + qwen3-vl:8b run error #8943

Open
opened 2026-04-12 21:45:54 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @crackerfly on GitHub (Dec 30, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13585

What is the issue?

time=2025-12-30T13:16:36.224+08:00 level=INFO source=routes.go:1554 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES:0 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:20m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\Program Files\StarSoftComm\ZhanAI\Ollama\Models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES:]"
time=2025-12-30T13:16:36.231+08:00 level=INFO source=images.go:493 msg="total blobs: 20"
time=2025-12-30T13:16:36.231+08:00 level=INFO source=images.go:500 msg="total unused blobs removed: 0"
time=2025-12-30T13:16:36.232+08:00 level=INFO source=routes.go:1607 msg="Listening on 127.0.0.1:11434 (version 0.13.5)"
time=2025-12-30T13:16:36.232+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2025-12-30T13:16:36.233+08:00 level=WARN source=runner.go:485 msg="user overrode visible devices" GGML_VK_VISIBLE_DEVICES=0
time=2025-12-30T13:16:36.234+08:00 level=WARN source=runner.go:489 msg="if GPUs are not correctly discovered, unset and try again"
time=2025-12-30T13:16:36.238+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\ollama.exe runner --ollama-engine --port 51381"
time=2025-12-30T13:16:36.664+08:00 level=INFO source=types.go:42 msg="inference compute" id=8680517d-0300-0000-0002-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="Intel(R) Arc(TM) 140T GPU (16GB)" libdirs=ollama,vulkan driver=0.0 pci_id="" type=iGPU total="18.0 GiB" available="17.1 GiB"
time=2025-12-30T13:16:36.665+08:00 level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="18.0 GiB" threshold="20.0 GiB"
[GIN] 2025/12/30 - 13:17:02 | 200 | 0s | 127.0.0.1 | HEAD "/"
time=2025-12-30T13:17:05.997+08:00 level=INFO source=download.go:177 msg="downloading ed12a4674d72 in 16 383 MB part(s)"
[GIN] 2025/12/30 - 13:42:07 | 200 | 25m5s | 127.0.0.1 | POST "/api/pull"
[GIN] 2025/12/30 - 13:42:10 | 200 | 0s | 127.0.0.1 | HEAD "/"
time=2025-12-30T13:42:12.169+08:00 level=INFO source=download.go:177 msg="downloading ed12a4674d72 in 16 383 MB part(s)"
time=2025-12-30T13:44:10.827+08:00 level=INFO source=download.go:177 msg="downloading 17e666fbe4f4 in 1 551 B part(s)"
[GIN] 2025/12/30 - 13:44:16 | 200 | 2m6s | 127.0.0.1 | POST "/api/pull"
[GIN] 2025/12/30 - 13:46:52 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/12/30 - 13:46:53 | 200 | 407.5252ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/12/30 - 13:46:53 | 200 | 29.2071ms | 127.0.0.1 | POST "/api/show"
time=2025-12-30T13:46:53.126+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\ollama.exe runner --ollama-engine --port 55745"
time=2025-12-30T13:46:54.259+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2025-12-30T13:46:54.259+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-12-30T13:46:54.260+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=16 efficiency=10 threads=16
time=2025-12-30T13:46:54.302+08:00 level=INFO source=server.go:245 msg="enabling flash attention"
time=2025-12-30T13:46:54.303+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\ollama.exe runner --ollama-engine --model C:\Program Files\StarSoftComm\ZhanAI\Ollama\Models\blobs\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 --port 55753"
time=2025-12-30T13:46:54.305+08:00 level=INFO source=sched.go:443 msg="system memory" total="31.4 GiB" free="21.4 GiB" free_swap="20.7 GiB"
time=2025-12-30T13:46:54.305+08:00 level=INFO source=sched.go:450 msg="gpu memory" id=8680517d-0300-0000-0002-000000000000 library=Vulkan available="16.6 GiB" free="17.1 GiB" minimum="457.0 MiB" overhead="0 B"
time=2025-12-30T13:46:54.306+08:00 level=INFO source=server.go:746 msg="loading model" "model layers"=37 requested=-1
time=2025-12-30T13:46:54.332+08:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2025-12-30T13:46:54.336+08:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:55753"
time=2025-12-30T13:46:54.339+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-12-30T13:46:54.357+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=858 num_key_values=40
load_backend: loaded CPU backend from C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\lib\ollama\ggml-cpu-alderlake.dll
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Intel(R) Arc(TM) 140T GPU (16GB) (Intel Corporation) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none
load_backend: loaded Vulkan backend from C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\lib\ollama\vulkan\ggml-vulkan.dll
time=2025-12-30T13:46:54.475+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000
ggml_backend_vk_get_device_memory called: luid 0x0000000000013dcd
ggml_dxgi_pdh_init called
DXGI + PDH Initialized. Getting GPU free memory info
[DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (16GB), LUID: 0x0000000000013DCD, Dedicated: 0.12 GB, Shared: 17.92 GB
[DXGI] Adapter Description: NVIDIA RTX PRO 500 Blackwell Generation Laptop GPU, LUID: 0x00000000000142D5, Dedicated: 5.65 GB, Shared: 17.92 GB
[DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000014242, Dedicated: 0.00 GB, Shared: 17.92 GB
Integrated GPU (Intel(R) Arc(TM) 140T GPU (16GB)) with LUID 0x0000000000013dcd detected. Shared Total: 19238452346.00 bytes (17.92 GB), Shared Usage: 1031168000.00 bytes (0.96 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB)
ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 18341502074 total: 19372670074
time=2025-12-30T13:46:54.828+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000
ggml_backend_vk_get_device_memory called: luid 0x0000000000013dcd
ggml_dxgi_pdh_init called
DXGI + PDH Initialized. Getting GPU free memory info
[DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (16GB), LUID: 0x0000000000013DCD, Dedicated: 0.12 GB, Shared: 17.92 GB
[DXGI] Adapter Description: NVIDIA RTX PRO 500 Blackwell Generation Laptop GPU, LUID: 0x00000000000142D5, Dedicated: 5.65 GB, Shared: 17.92 GB
[DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000014242, Dedicated: 0.00 GB, Shared: 17.92 GB
Integrated GPU (Intel(R) Arc(TM) 140T GPU (16GB)) with LUID 0x0000000000013dcd detected. Shared Total: 19238452346.00 bytes (17.92 GB), Shared Usage: 1031168000.00 bytes (0.96 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB)
ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 18341502074 total: 19372670074
time=2025-12-30T13:46:55.439+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-12-30T13:46:55.439+08:00 level=INFO source=ggml.go:482 msg="offloading 36 repeating layers to GPU"
time=2025-12-30T13:46:55.439+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2025-12-30T13:46:55.439+08:00 level=INFO source=ggml.go:494 msg="offloaded 37/37 layers to GPU"
time=2025-12-30T13:46:55.439+08:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="5.4 GiB"
time=2025-12-30T13:46:55.440+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="333.8 MiB"
time=2025-12-30T13:46:55.440+08:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="576.0 MiB"
time=2025-12-30T13:46:55.440+08:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="490.7 MiB"
time=2025-12-30T13:46:55.440+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="63.3 MiB"
time=2025-12-30T13:46:55.440+08:00 level=INFO source=device.go:272 msg="total memory" size="6.8 GiB"
time=2025-12-30T13:46:55.440+08:00 level=INFO source=sched.go:517 msg="loaded runners" count=1
time=2025-12-30T13:46:55.440+08:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding"
time=2025-12-30T13:46:55.440+08:00 level=INFO source=server.go:1372 msg="waiting for server to become available" status="llm server loading model"
time=2025-12-30T13:47:01.696+08:00 level=INFO source=server.go:1376 msg="llama runner started in 7.39 seconds"
[GIN] 2025/12/30 - 13:47:01 | 200 | 8.6300157s | 127.0.0.1 | POST "/api/generate"
Exception 0xe06d7363 0x19930520 0xfec79ff980 0x7ff845f2782a
PC=0x7ff845f2782a
signal arrived during external code execution

runtime.cgocall(0x7ff63984b300, 0xc0004715a8)
runtime/cgocall.go:167 +0x3e fp=0xc000471580 sp=0xc000471518 pc=0x7ff638ae243e
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_synchronize(0x2f9f30afcf0)
cgo_gotypes.go:1035 +0x45 fp=0xc0004715a8 sp=0xc000471580 pc=0x7ff638f30a45
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func4.1(...)
github.com/ollama/ollama/ml/backend/ggml/ggml.go:833
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func4()
github.com/ollama/ollama/ml/backend/ggml/ggml.go:833 +0x55 fp=0xc0004715f0 sp=0xc0004715a8 pc=0x7ff638f3eed5
github.com/ollama/ollama/ml/backend/ggml.(*Tensor).Floats(0xc008242570)
github.com/ollama/ollama/ml/backend/ggml/ggml.go:1065 +0xac fp=0xc000471678 sp=0xc0004715f0 pc=0x7ff638f40e8c
github.com/ollama/ollama/runner/ollamarunner.multimodalStore.getTensor(0x7ff639cb21a0?, {0x7ff63a068050, 0xc0000cd760}, {0x7ff63a06d2a0, 0xc000644500}, {0x7ff63a079f68, 0xc008242570}, 0x0)
github.com/ollama/ollama/runner/ollamarunner/multimodal.go:97 +0x38e fp=0xc000471788 sp=0xc000471678 pc=0x7ff6390147ae
github.com/ollama/ollama/runner/ollamarunner.multimodalStore.getMultimodal(0xc0005899e0, {0x7ff63a068050, 0xc0000cd760}, {0x7ff63a06d2a0, 0xc000644500}, {0xc000050100, 0x4, 0x0?}, 0x0)
github.com/ollama/ollama/runner/ollamarunner/multimodal.go:56 +0xe5 fp=0xc0004717f0 sp=0xc000471788 pc=0x7ff639014305
github.com/ollama/ollama/runner/ollamarunner.(*Server).forwardBatch(
, {0x0, {0x0, 0x0}, {0x0, 0x0}, {0x0, 0x0, 0x0}, {{0x0, ...}, ...}, ...})
github.com/ollama/ollama/runner/ollamarunner/runner.go:584 +0x1217 fp=0xc000471b58 sp=0xc0004717f0 pc=0x7ff639017977
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc000202b40, {0x7ff63a061b10, 0xc00059f7c0})
github.com/ollama/ollama/runner/ollamarunner/runner.go:452 +0x18c fp=0xc000471fb8 sp=0xc000471b58 pc=0x7ff63901650c
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
github.com/ollama/ollama/runner/ollamarunner/runner.go:1418 +0x28 fp=0xc000471fe0 sp=0xc000471fb8 pc=0x7ff63901fc08
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000471fe8 sp=0xc000471fe0 pc=0x7ff638aed8e1
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
github.com/ollama/ollama/runner/ollamarunner/runner.go:1418 +0x4c9

goroutine 1 gp=0xc0000021c0 m=nil [IO wait]:
runtime.gopark(0x7ff638aef0e0?, 0x7ff63aa0ab80?, 0xa0?, 0xb1?, 0xc00064b24c?)
runtime/proc.go:435 +0xce fp=0xc000131648 sp=0xc000131628 pc=0x7ff638ae598e
runtime.netpollblock(0x224?, 0x38a80406?, 0xf6?)
runtime/netpoll.go:575 +0xf7 fp=0xc000131680 sp=0xc000131648 pc=0x7ff638aabdf7
internal/poll.runtime_pollWait(0x2f9ebe7d130, 0x72)
runtime/netpoll.go:351 +0x85 fp=0xc0001316a0 sp=0xc000131680 pc=0x7ff638ae4b25
internal/poll.(*pollDesc).wait(0x7ff638b7a7b3?, 0x0?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0001316c8 sp=0xc0001316a0 pc=0x7ff638b7bda7
internal/poll.execIO(0xc00064b1a0, 0xc00011f770)
internal/poll/fd_windows.go:177 +0x105 fp=0xc000131740 sp=0xc0001316c8 pc=0x7ff638b7d205
internal/poll.(*FD).acceptOne(0xc00064b188, 0x234, {0xc0006760f0?, 0xc00011f7d0?, 0x7ff638b84ec5?}, 0xc00011f804?)
internal/poll/fd_windows.go:946 +0x65 fp=0xc0001317a0 sp=0xc000131740 pc=0x7ff638b81785
internal/poll.(*FD).Accept(0xc00064b188, 0xc000131950)
internal/poll/fd_windows.go:980 +0x1b6 fp=0xc000131858 sp=0xc0001317a0 pc=0x7ff638b81ab6
net.(*netFD).accept(0xc00064b188)
net/fd_windows.go:182 +0x4b fp=0xc000131970 sp=0xc000131858 pc=0x7ff638bf302b
net.(*TCPListener).accept(0xc00059db00)
net/tcpsock_posix.go:159 +0x1b fp=0xc0001319c0 sp=0xc000131970 pc=0x7ff638c0907b
net.(*TCPListener).Accept(0xc00059db00)
net/tcpsock.go:380 +0x30 fp=0xc0001319f0 sp=0xc0001319c0 pc=0x7ff638c07e30
net/http.(*onceCloseListener).Accept(0xc00065c3f0?)
:1 +0x24 fp=0xc000131a08 sp=0xc0001319f0 pc=0x7ff638e212a4
net/http.(*Server).Serve(0xc000117000, {0x7ff63a05f4e0, 0xc00059db00})
net/http/server.go:3424 +0x30c fp=0xc000131b38 sp=0xc000131a08 pc=0x7ff638df8b6c
github.com/ollama/ollama/runner/ollamarunner.Execute({0xc0000500b0, 0x4, 0x5})
github.com/ollama/ollama/runner/ollamarunner/runner.go:1441 +0x94e fp=0xc000131d08 sp=0xc000131b38 pc=0x7ff63901f98e
github.com/ollama/ollama/runner.Execute({0xc000050090?, 0x0?, 0x0?})
github.com/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc000131d30 sp=0xc000131d08 pc=0x7ff639020289
github.com/ollama/ollama/cmd.NewCLI.func2(0xc000116d00?, {0x7ff639e713ff?, 0x4?, 0x7ff639e71403?})
github.com/ollama/ollama/cmd/cmd.go:1841 +0x45 fp=0xc000131d58 sp=0xc000131d30 pc=0x7ff6397ddb45
github.com/spf13/cobra.(*Command).execute(0xc000469b08, {0xc00059f720, 0x5, 0x5})
github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000131e78 sp=0xc000131d58 pc=0x7ff638c6dafc
github.com/spf13/cobra.(*Command).ExecuteC(0xc0005c4608)
github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000131f30 sp=0xc000131e78 pc=0x7ff638c6e345
github.com/spf13/cobra.(*Command).Execute(...)
github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000131f50 sp=0xc000131f30 pc=0x7ff6397de62d
runtime.main()
runtime/proc.go:283 +0x27d fp=0xc000131fe0 sp=0xc000131f50 pc=0x7ff638ab4ddd
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000131fe8 sp=0xc000131fe0 pc=0x7ff638aed8e1

goroutine 2 gp=0xc0000028c0 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000081fa8 sp=0xc000081f88 pc=0x7ff638ae598e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.forcegchelper()
runtime/proc.go:348 +0xb8 fp=0xc000081fe0 sp=0xc000081fa8 pc=0x7ff638ab50f8
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff638aed8e1
created by runtime.init.7 in goroutine 1
runtime/proc.go:336 +0x1a

goroutine 3 gp=0xc000002c40 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000083f80 sp=0xc000083f60 pc=0x7ff638ae598e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.bgsweep(0xc00008c000)
runtime/mgcsweep.go:316 +0xdf fp=0xc000083fc8 sp=0xc000083f80 pc=0x7ff638a9debf
runtime.gcenable.gowrap1()
runtime/mgc.go:204 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff638a92285
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff638aed8e1
created by runtime.gcenable in goroutine 1
runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000002e00 m=nil [GC scavenge wait]:
runtime.gopark(0x3a2528?, 0x4c3beb?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000093f78 sp=0xc000093f58 pc=0x7ff638ae598e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.(*scavengerState).park(0x7ff63aa31580)
runtime/mgcscavenge.go:425 +0x49 fp=0xc000093fa8 sp=0xc000093f78 pc=0x7ff638a9b909
runtime.bgscavenge(0xc00008c000)
runtime/mgcscavenge.go:658 +0x59 fp=0xc000093fc8 sp=0xc000093fa8 pc=0x7ff638a9be99
runtime.gcenable.gowrap2()
runtime/mgc.go:205 +0x25 fp=0xc000093fe0 sp=0xc000093fc8 pc=0x7ff638a92225
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000093fe8 sp=0xc000093fe0 pc=0x7ff638aed8e1
created by runtime.gcenable in goroutine 1
runtime/mgc.go:205 +0xa5

goroutine 5 gp=0xc000003340 m=nil [finalizer wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000095e30 sp=0xc000095e10 pc=0x7ff638ae598e
runtime.runfinq()
runtime/mfinal.go:196 +0x107 fp=0xc000095fe0 sp=0xc000095e30 pc=0x7ff638a91207
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000095fe8 sp=0xc000095fe0 pc=0x7ff638aed8e1
created by runtime.createfing in goroutine 1
runtime/mfinal.go:166 +0x3d

goroutine 6 gp=0xc000003dc0 m=nil [chan receive]:
runtime.gopark(0xc0001ff720?, 0xc0082a0060?, 0x60?, 0x5f?, 0x7ff638bdbf68?)
runtime/proc.go:435 +0xce fp=0xc000085f18 sp=0xc000085ef8 pc=0x7ff638ae598e
runtime.chanrecv(0xc00003a380, 0x0, 0x1)
runtime/chan.go:664 +0x445 fp=0xc000085f90 sp=0xc000085f18 pc=0x7ff638a82d45
runtime.chanrecv1(0x7ff638ab4f40?, 0xc000085f76?)
runtime/chan.go:506 +0x12 fp=0xc000085fb8 sp=0xc000085f90 pc=0x7ff638a828d2
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
runtime/mgc.go:1799 +0x2f fp=0xc000085fe0 sp=0xc000085fb8 pc=0x7ff638a954af
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff638aed8e1
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
runtime/mgc.go:1794 +0x85

goroutine 7 gp=0xc0003f6380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00008ff38 sp=0xc00008ff18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc00008ffc8 sp=0xc00008ff38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00008ffe0 sp=0xc00008ffc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00008ffe8 sp=0xc00008ffe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 18 gp=0xc000484000 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00048bf38 sp=0xc00048bf18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc00048bfc8 sp=0xc00048bf38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00048bfe0 sp=0xc00048bfc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00048bfe8 sp=0xc00048bfe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 34 gp=0xc0001061c0 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000487f38 sp=0xc000487f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc000487fc8 sp=0xc000487f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000487fe0 sp=0xc000487fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000487fe8 sp=0xc000487fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 35 gp=0xc000106380 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x3?, 0x80?, 0xf0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000489f38 sp=0xc000489f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc000489fc8 sp=0xc000489f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000489fe0 sp=0xc000489fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000489fe8 sp=0xc000489fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 8 gp=0xc0003f6540 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000091f38 sp=0xc000091f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc000091fc8 sp=0xc000091f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000091fe0 sp=0xc000091fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000091fe8 sp=0xc000091fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 19 gp=0xc0004841c0 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8df8f170?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 36 gp=0xc000106540 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000113f38 sp=0xc000113f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc000113fc8 sp=0xc000113f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000113fe0 sp=0xc000113fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000113fe8 sp=0xc000113fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 9 gp=0xc0003f6700 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8df0f7a4?, 0x1?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00010ff38 sp=0xc00010ff18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc00010ffc8 sp=0xc00010ff38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00010ffe0 sp=0xc00010ffc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00010ffe8 sp=0xc00010ffe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 20 gp=0xc000484380 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x3?, 0x0?, 0x1b?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000495f38 sp=0xc000495f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc000495fc8 sp=0xc000495f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000495fe0 sp=0xc000495fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000495fe8 sp=0xc000495fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 37 gp=0xc000106700 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x1?, 0xa0?, 0xc6?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000115f38 sp=0xc000115f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc000115fc8 sp=0xc000115f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000115fe0 sp=0xc000115fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000115fe8 sp=0xc000115fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 10 gp=0xc0003f68c0 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x1?, 0xcc?, 0xa3?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000111f38 sp=0xc000111f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc000111fc8 sp=0xc000111f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000111fe0 sp=0xc000111fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000111fe8 sp=0xc000111fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 21 gp=0xc000484540 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x3?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000497f38 sp=0xc000497f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc000497fc8 sp=0xc000497f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000497fe0 sp=0xc000497fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000497fe8 sp=0xc000497fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 38 gp=0xc0001068c0 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x1?, 0x64?, 0xfe?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000491f38 sp=0xc000491f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc000491fc8 sp=0xc000491f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000491fe0 sp=0xc000491fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000491fe8 sp=0xc000491fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 11 gp=0xc0003f6a80 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8ddbe6ac?, 0x1?, 0xc8?, 0x13?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000473f38 sp=0xc000473f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc000473fc8 sp=0xc000473f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000473fe0 sp=0xc000473fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000473fe8 sp=0xc000473fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 22 gp=0xc000484700 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x3?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00046ff38 sp=0xc00046ff18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc00046ffc8 sp=0xc00046ff38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00046ffe0 sp=0xc00046ffc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00046ffe8 sp=0xc00046ffe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 39 gp=0xc000106a80 m=nil [GC worker (idle)]:
runtime.gopark(0x4ae8de0d20c?, 0x3?, 0x44?, 0x14?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000493f38 sp=0xc000493f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b960)
runtime/mgc.go:1423 +0xe9 fp=0xc000493fc8 sp=0xc000493f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000493fe0 sp=0xc000493fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000493fe8 sp=0xc000493fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 13 gp=0xc000107180 m=nil [select]:
runtime.gopark(0xc000049a08?, 0x2?, 0x0?, 0x91?, 0xc00004986c?)
runtime/proc.go:435 +0xce fp=0xc000049698 sp=0xc000049678 pc=0x7ff638ae598e
runtime.selectgo(0xc000049a08, 0xc000049868, 0x141?, 0x0, 0x1?, 0x1)
runtime/select.go:351 +0x837 fp=0xc0000497d0 sp=0xc000049698 pc=0x7ff638ac6437
github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc000202b40, {0x7ff63a05f690, 0xc00039c000}, 0xc0003643c0)
github.com/ollama/ollama/runner/ollamarunner/runner.go:950 +0xc4e fp=0xc000049ac0 sp=0xc0000497d0 pc=0x7ff63901ac2e
github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x7ff63a05f690?, 0xc00039c000?}, 0xc000049b40?)
:1 +0x36 fp=0xc000049af0 sp=0xc000049ac0 pc=0x7ff6390200f6
net/http.HandlerFunc.ServeHTTP(0xc0005aed80?, {0x7ff63a05f690?, 0xc00039c000?}, 0xc000049b60?)
net/http/server.go:2294 +0x29 fp=0xc000049b18 sp=0xc000049af0 pc=0x7ff638df51a9
net/http.(*ServeMux).ServeHTTP(0x7ff638a8b785?, {0x7ff63a05f690, 0xc00039c000}, 0xc0003643c0)
net/http/server.go:2822 +0x1c4 fp=0xc000049b68 sp=0xc000049b18 pc=0x7ff638df70a4
net/http.serverHandler.ServeHTTP({0x7ff63a05bc30?}, {0x7ff63a05f690?, 0xc00039c000?}, 0x1?)
net/http/server.go:3301 +0x8e fp=0xc000049b98 sp=0xc000049b68 pc=0x7ff638e14b2e
net/http.(*conn).serve(0xc00065c3f0, {0x7ff63a061ad8, 0xc000252f90})
net/http/server.go:2102 +0x625 fp=0xc000049fb8 sp=0xc000049b98 pc=0x7ff638df36a5
net/http.(*Server).Serve.gowrap3()
net/http/server.go:3454 +0x28 fp=0xc000049fe0 sp=0xc000049fb8 pc=0x7ff638df8f68
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x7ff638aed8e1
created by net/http.(*Server).Serve in goroutine 1
net/http/server.go:3454 +0x485

goroutine 911 gp=0xc0005ca380 m=nil [IO wait]:
runtime.gopark(0x0?, 0xc00064b420?, 0xc8?, 0xb4?, 0xc00064b4cc?)
runtime/proc.go:435 +0xce fp=0xc000575d58 sp=0xc000575d38 pc=0x7ff638ae598e
runtime.netpollblock(0x214?, 0x38a80406?, 0xf6?)
runtime/netpoll.go:575 +0xf7 fp=0xc000575d90 sp=0xc000575d58 pc=0x7ff638aabdf7
internal/poll.runtime_pollWait(0x2f9ebe7d018, 0x72)
runtime/netpoll.go:351 +0x85 fp=0xc000575db0 sp=0xc000575d90 pc=0x7ff638ae4b25
internal/poll.(*pollDesc).wait(0x214?, 0x72?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000575dd8 sp=0xc000575db0 pc=0x7ff638b7bda7
internal/poll.execIO(0xc00064b420, 0x7ff639eea258)
internal/poll/fd_windows.go:177 +0x105 fp=0xc000575e50 sp=0xc000575dd8 pc=0x7ff638b7d205
internal/poll.(*FD).Read(0xc00064b408, {0xc0003340a1, 0x1, 0x1})
internal/poll/fd_windows.go:438 +0x29b fp=0xc000575ef0 sp=0xc000575e50 pc=0x7ff638b7dedb
net.(*netFD).Read(0xc00064b408, {0xc0003340a1?, 0xc000644298?, 0xc000575f70?})
net/fd_posix.go:55 +0x25 fp=0xc000575f38 sp=0xc000575ef0 pc=0x7ff638bf1145
net.(*conn).Read(0xc0005963d8, {0xc0003340a1?, 0xff000000ff000000?, 0xff000000ff000000?})
net/net.go:194 +0x45 fp=0xc000575f80 sp=0xc000575f38 pc=0x7ff638c00625
net/http.(*connReader).backgroundRead(0xc000334090)
net/http/server.go:690 +0x37 fp=0xc000575fc8 sp=0xc000575f80 pc=0x7ff638ded577
net/http.(*connReader).startBackgroundRead.gowrap2()
net/http/server.go:686 +0x25 fp=0xc000575fe0 sp=0xc000575fc8 pc=0x7ff638ded4a5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000575fe8 sp=0xc000575fe0 pc=0x7ff638aed8e1
created by net/http.(*connReader).startBackgroundRead in goroutine 13
net/http/server.go:686 +0xb6
rax 0x0
rbx 0xfec79ff908
rcx 0x0
rdx 0x2f9e6860000
rdi 0xe06d7363
rsi 0x1
rbp 0x4
rsp 0xfec79ff7e0
r8 0x1
r9 0xe06d7363
r10 0x0
r11 0x90000
r12 0x0
r13 0x7ff63a96b780
r14 0xc000106fc0
r15 0x0
rip 0x7ff845f2782a
rflags 0x202
cs 0x33
fs 0x53
gs 0x2b
time=2025-12-30T13:47:36.508+08:00 level=ERROR source=server.go:1583 msg="post predict" error="Post "http://127.0.0.1:55753/completion": read tcp 127.0.0.1:55757->127.0.0.1:55753: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2025/12/30 - 13:47:36 | 500 | 8.7242091s | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/12/30 - 13:48:08 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/12/30 - 13:48:08 | 200 | 29.268ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/12/30 - 13:48:08 | 200 | 28.8107ms | 127.0.0.1 | POST "/api/show"
time=2025-12-30T13:48:08.738+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\ollama.exe runner --ollama-engine --port 55849"
time=2025-12-30T13:48:09.145+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2025-12-30T13:48:09.146+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-12-30T13:48:09.147+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=16 efficiency=10 threads=16
time=2025-12-30T13:48:09.191+08:00 level=INFO source=server.go:245 msg="enabling flash attention"
time=2025-12-30T13:48:09.192+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\ollama.exe runner --ollama-engine --model C:\Program Files\StarSoftComm\ZhanAI\Ollama\Models\blobs\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 --port 55854"
time=2025-12-30T13:48:09.194+08:00 level=INFO source=sched.go:443 msg="system memory" total="31.4 GiB" free="21.6 GiB" free_swap="20.7 GiB"
time=2025-12-30T13:48:09.195+08:00 level=INFO source=sched.go:450 msg="gpu memory" id=8680517d-0300-0000-0002-000000000000 library=Vulkan available="16.6 GiB" free="17.0 GiB" minimum="457.0 MiB" overhead="0 B"
time=2025-12-30T13:48:09.195+08:00 level=INFO source=server.go:746 msg="loading model" "model layers"=37 requested=-1
time=2025-12-30T13:48:09.222+08:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2025-12-30T13:48:09.226+08:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:55854"
time=2025-12-30T13:48:09.227+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-12-30T13:48:09.245+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=858 num_key_values=40
load_backend: loaded CPU backend from C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\lib\ollama\ggml-cpu-alderlake.dll
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Intel(R) Arc(TM) 140T GPU (16GB) (Intel Corporation) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none
load_backend: loaded Vulkan backend from C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\lib\ollama\vulkan\ggml-vulkan.dll
time=2025-12-30T13:48:09.363+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000
ggml_backend_vk_get_device_memory called: luid 0x0000000000013dcd
ggml_dxgi_pdh_init called
DXGI + PDH Initialized. Getting GPU free memory info
[DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (16GB), LUID: 0x0000000000013DCD, Dedicated: 0.12 GB, Shared: 17.92 GB
[DXGI] Adapter Description: NVIDIA RTX PRO 500 Blackwell Generation Laptop GPU, LUID: 0x00000000000142D5, Dedicated: 5.65 GB, Shared: 17.92 GB
[DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000014242, Dedicated: 0.00 GB, Shared: 17.92 GB
Integrated GPU (Intel(R) Arc(TM) 140T GPU (16GB)) with LUID 0x0000000000013dcd detected. Shared Total: 19238452346.00 bytes (17.92 GB), Shared Usage: 1090072576.00 bytes (1.02 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB)
ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 18282597498 total: 19372670074
time=2025-12-30T13:48:09.719+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000
ggml_backend_vk_get_device_memory called: luid 0x0000000000013dcd
ggml_dxgi_pdh_init called
DXGI + PDH Initialized. Getting GPU free memory info
[DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (16GB), LUID: 0x0000000000013DCD, Dedicated: 0.12 GB, Shared: 17.92 GB
[DXGI] Adapter Description: NVIDIA RTX PRO 500 Blackwell Generation Laptop GPU, LUID: 0x00000000000142D5, Dedicated: 5.65 GB, Shared: 17.92 GB
[DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000014242, Dedicated: 0.00 GB, Shared: 17.92 GB
Integrated GPU (Intel(R) Arc(TM) 140T GPU (16GB)) with LUID 0x0000000000013dcd detected. Shared Total: 19238452346.00 bytes (17.92 GB), Shared Usage: 1090072576.00 bytes (1.02 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB)
ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 18282597498 total: 19372670074
time=2025-12-30T13:48:10.277+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-12-30T13:48:10.277+08:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="5.4 GiB"
time=2025-12-30T13:48:10.277+08:00 level=INFO source=ggml.go:482 msg="offloading 36 repeating layers to GPU"
time=2025-12-30T13:48:10.277+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2025-12-30T13:48:10.277+08:00 level=INFO source=ggml.go:494 msg="offloaded 37/37 layers to GPU"
time=2025-12-30T13:48:10.278+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="333.8 MiB"
time=2025-12-30T13:48:10.278+08:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="576.0 MiB"
time=2025-12-30T13:48:10.278+08:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="490.7 MiB"
time=2025-12-30T13:48:10.278+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="63.3 MiB"
time=2025-12-30T13:48:10.278+08:00 level=INFO source=device.go:272 msg="total memory" size="6.8 GiB"
time=2025-12-30T13:48:10.278+08:00 level=INFO source=sched.go:517 msg="loaded runners" count=1
time=2025-12-30T13:48:10.278+08:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding"
time=2025-12-30T13:48:10.279+08:00 level=INFO source=server.go:1372 msg="waiting for server to become available" status="llm server loading model"
time=2025-12-30T13:48:16.538+08:00 level=INFO source=server.go:1376 msg="llama runner started in 7.34 seconds"
[GIN] 2025/12/30 - 13:48:16 | 200 | 7.8534757s | 127.0.0.1 | POST "/api/generate"
Exception 0xe06d7363 0x19930520 0x3bbb9ff950 0x7ff845f2782a
PC=0x7ff845f2782a
signal arrived during external code execution

runtime.cgocall(0x7ff63984b300, 0xc0004715a8)
runtime/cgocall.go:167 +0x3e fp=0xc000471580 sp=0xc000471518 pc=0x7ff638ae243e
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_synchronize(0x22066ef23b0)
cgo_gotypes.go:1035 +0x45 fp=0xc0004715a8 sp=0xc000471580 pc=0x7ff638f30a45
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func4.1(...)
github.com/ollama/ollama/ml/backend/ggml/ggml.go:833
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func4()
github.com/ollama/ollama/ml/backend/ggml/ggml.go:833 +0x55 fp=0xc0004715f0 sp=0xc0004715a8 pc=0x7ff638f3eed5
github.com/ollama/ollama/ml/backend/ggml.(*Tensor).Floats(0xc000f0a600)
github.com/ollama/ollama/ml/backend/ggml/ggml.go:1065 +0xac fp=0xc000471678 sp=0xc0004715f0 pc=0x7ff638f40e8c
github.com/ollama/ollama/runner/ollamarunner.multimodalStore.getTensor(0x7ff639cb21a0?, {0x7ff63a068050, 0xc0000cd760}, {0x7ff63a06d2a0, 0xc0000c0000}, {0x7ff63a079f68, 0xc000f0a600}, 0x0)
github.com/ollama/ollama/runner/ollamarunner/multimodal.go:97 +0x38e fp=0xc000471788 sp=0xc000471678 pc=0x7ff6390147ae
github.com/ollama/ollama/runner/ollamarunner.multimodalStore.getMultimodal(0xc00045e9f0, {0x7ff63a068050, 0xc0000cd760}, {0x7ff63a06d2a0, 0xc0000c0000}, {0xc000050100, 0x4, 0x0?}, 0x0)
github.com/ollama/ollama/runner/ollamarunner/multimodal.go:56 +0xe5 fp=0xc0004717f0 sp=0xc000471788 pc=0x7ff639014305
github.com/ollama/ollama/runner/ollamarunner.(*Server).forwardBatch(
, {0x0, {0x0, 0x0}, {0x0, 0x0}, {0x0, 0x0, 0x0}, {{0x0, ...}, ...}, ...})
github.com/ollama/ollama/runner/ollamarunner/runner.go:584 +0x1217 fp=0xc000471b58 sp=0xc0004717f0 pc=0x7ff639017977
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc000202f00, {0x7ff63a061b10, 0xc0000ddae0})
github.com/ollama/ollama/runner/ollamarunner/runner.go:452 +0x18c fp=0xc000471fb8 sp=0xc000471b58 pc=0x7ff63901650c
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
github.com/ollama/ollama/runner/ollamarunner/runner.go:1418 +0x28 fp=0xc000471fe0 sp=0xc000471fb8 pc=0x7ff63901fc08
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000471fe8 sp=0xc000471fe0 pc=0x7ff638aed8e1
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
github.com/ollama/ollama/runner/ollamarunner/runner.go:1418 +0x4c9

goroutine 1 gp=0xc0000021c0 m=nil [IO wait]:
runtime.gopark(0x7ff638aef0e0?, 0x7ff63aa0ab80?, 0x20?, 0xd4?, 0xc00068d4cc?)
runtime/proc.go:435 +0xce fp=0xc0006d3648 sp=0xc0006d3628 pc=0x7ff638ae598e
runtime.netpollblock(0x1cc?, 0x38a80406?, 0xf6?)
runtime/netpoll.go:575 +0xf7 fp=0xc0006d3680 sp=0xc0006d3648 pc=0x7ff638aabdf7
internal/poll.runtime_pollWait(0x220619a6d70, 0x72)
runtime/netpoll.go:351 +0x85 fp=0xc0006d36a0 sp=0xc0006d3680 pc=0x7ff638ae4b25
internal/poll.(*pollDesc).wait(0x7ff638b7a7b3?, 0x0?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0006d36c8 sp=0xc0006d36a0 pc=0x7ff638b7bda7
internal/poll.execIO(0xc00068d420, 0xc00050f770)
internal/poll/fd_windows.go:177 +0x105 fp=0xc0006d3740 sp=0xc0006d36c8 pc=0x7ff638b7d205
internal/poll.(*FD).acceptOne(0xc00068d408, 0x22c, {0xc0006cc0f0?, 0xc00050f7d0?, 0x7ff638b84ec5?}, 0xc00050f804?)
internal/poll/fd_windows.go:946 +0x65 fp=0xc0006d37a0 sp=0xc0006d3740 pc=0x7ff638b81785
internal/poll.(*FD).Accept(0xc00068d408, 0xc0006d3950)
internal/poll/fd_windows.go:980 +0x1b6 fp=0xc0006d3858 sp=0xc0006d37a0 pc=0x7ff638b81ab6
net.(*netFD).accept(0xc00068d408)
net/fd_windows.go:182 +0x4b fp=0xc0006d3970 sp=0xc0006d3858 pc=0x7ff638bf302b
net.(*TCPListener).accept(0xc0002c0940)
net/tcpsock_posix.go:159 +0x1b fp=0xc0006d39c0 sp=0xc0006d3970 pc=0x7ff638c0907b
net.(*TCPListener).Accept(0xc0002c0940)
net/tcpsock.go:380 +0x30 fp=0xc0006d39f0 sp=0xc0006d39c0 pc=0x7ff638c07e30
net/http.(*onceCloseListener).Accept(0xc0006ae3f0?)
:1 +0x24 fp=0xc0006d3a08 sp=0xc0006d39f0 pc=0x7ff638e212a4
net/http.(*Server).Serve(0xc0001cd700, {0x7ff63a05f4e0, 0xc0002c0940})
net/http/server.go:3424 +0x30c fp=0xc0006d3b38 sp=0xc0006d3a08 pc=0x7ff638df8b6c
github.com/ollama/ollama/runner/ollamarunner.Execute({0xc0000500b0, 0x4, 0x5})
github.com/ollama/ollama/runner/ollamarunner/runner.go:1441 +0x94e fp=0xc0006d3d08 sp=0xc0006d3b38 pc=0x7ff63901f98e
github.com/ollama/ollama/runner.Execute({0xc000050090?, 0x0?, 0x0?})
github.com/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc0006d3d30 sp=0xc0006d3d08 pc=0x7ff639020289
github.com/ollama/ollama/cmd.NewCLI.func2(0xc0001cd400?, {0x7ff639e713ff?, 0x4?, 0x7ff639e71403?})
github.com/ollama/ollama/cmd/cmd.go:1841 +0x45 fp=0xc0006d3d58 sp=0xc0006d3d30 pc=0x7ff6397ddb45
github.com/spf13/cobra.(*Command).execute(0xc0006b1508, {0xc0000dda40, 0x5, 0x5})
github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc0006d3e78 sp=0xc0006d3d58 pc=0x7ff638c6dafc
github.com/spf13/cobra.(*Command).ExecuteC(0xc00045af08)
github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc0006d3f30 sp=0xc0006d3e78 pc=0x7ff638c6e345
github.com/spf13/cobra.(*Command).Execute(...)
github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
github.com/ollama/ollama/main.go:12 +0x4d fp=0xc0006d3f50 sp=0xc0006d3f30 pc=0x7ff6397de62d
runtime.main()
runtime/proc.go:283 +0x27d fp=0xc0006d3fe0 sp=0xc0006d3f50 pc=0x7ff638ab4ddd
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0006d3fe8 sp=0xc0006d3fe0 pc=0x7ff638aed8e1

goroutine 2 gp=0xc0000028c0 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000081fa8 sp=0xc000081f88 pc=0x7ff638ae598e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.forcegchelper()
runtime/proc.go:348 +0xb8 fp=0xc000081fe0 sp=0xc000081fa8 pc=0x7ff638ab50f8
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff638aed8e1
created by runtime.init.7 in goroutine 1
runtime/proc.go:336 +0x1a

goroutine 3 gp=0xc000002c40 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000083f80 sp=0xc000083f60 pc=0x7ff638ae598e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.bgsweep(0xc00008c000)
runtime/mgcsweep.go:316 +0xdf fp=0xc000083fc8 sp=0xc000083f80 pc=0x7ff638a9debf
runtime.gcenable.gowrap1()
runtime/mgc.go:204 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff638a92285
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff638aed8e1
created by runtime.gcenable in goroutine 1
runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000002e00 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x4ca3d8?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000093f78 sp=0xc000093f58 pc=0x7ff638ae598e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.(*scavengerState).park(0x7ff63aa31580)
runtime/mgcscavenge.go:425 +0x49 fp=0xc000093fa8 sp=0xc000093f78 pc=0x7ff638a9b909
runtime.bgscavenge(0xc00008c000)
runtime/mgcscavenge.go:658 +0x59 fp=0xc000093fc8 sp=0xc000093fa8 pc=0x7ff638a9be99
runtime.gcenable.gowrap2()
runtime/mgc.go:205 +0x25 fp=0xc000093fe0 sp=0xc000093fc8 pc=0x7ff638a92225
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000093fe8 sp=0xc000093fe0 pc=0x7ff638aed8e1
created by runtime.gcenable in goroutine 1
runtime/mgc.go:205 +0xa5

goroutine 5 gp=0xc000003340 m=nil [finalizer wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000095e30 sp=0xc000095e10 pc=0x7ff638ae598e
runtime.runfinq()
runtime/mfinal.go:196 +0x107 fp=0xc000095fe0 sp=0xc000095e30 pc=0x7ff638a91207
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000095fe8 sp=0xc000095fe0 pc=0x7ff638aed8e1
created by runtime.createfing in goroutine 1
runtime/mfinal.go:166 +0x3d

goroutine 6 gp=0xc000003dc0 m=nil [chan receive]:
runtime.gopark(0xc0001ff720?, 0xc000f0a630?, 0x60?, 0x5f?, 0x7ff638bdbf68?)
runtime/proc.go:435 +0xce fp=0xc000085f18 sp=0xc000085ef8 pc=0x7ff638ae598e
runtime.chanrecv(0xc00003a380, 0x0, 0x1)
runtime/chan.go:664 +0x445 fp=0xc000085f90 sp=0xc000085f18 pc=0x7ff638a82d45
runtime.chanrecv1(0x7ff638ab4f40?, 0xc000085f76?)
runtime/chan.go:506 +0x12 fp=0xc000085fb8 sp=0xc000085f90 pc=0x7ff638a828d2
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
runtime/mgc.go:1799 +0x2f fp=0xc000085fe0 sp=0xc000085fb8 pc=0x7ff638a954af
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff638aed8e1
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
runtime/mgc.go:1794 +0x85

goroutine 7 gp=0xc0003f6380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00008ff38 sp=0xc00008ff18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc00008ffc8 sp=0xc00008ff38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00008ffe0 sp=0xc00008ffc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00008ffe8 sp=0xc00008ffe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 8 gp=0xc0003f6540 m=nil [GC worker (idle)]:
runtime.gopark(0x7ff63aa80160?, 0x1?, 0x70?, 0x65?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000091f38 sp=0xc000091f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc000091fc8 sp=0xc000091f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000091fe0 sp=0xc000091fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000091fe8 sp=0xc000091fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 18 gp=0xc000484000 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb50dd3d5c?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00048bf38 sp=0xc00048bf18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc00048bfc8 sp=0xc00048bf38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00048bfe0 sp=0xc00048bfc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00048bfe8 sp=0xc00048bfe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 9 gp=0xc0003f6700 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb50cdfab8?, 0x3?, 0x70?, 0x65?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000487f38 sp=0xc000487f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc000487fc8 sp=0xc000487f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000487fe0 sp=0xc000487fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000487fe8 sp=0xc000487fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 34 gp=0xc0001061c0 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb50dd3d5c?, 0x3?, 0x58?, 0x70?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000113f38 sp=0xc000113f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc000113fc8 sp=0xc000113f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000113fe0 sp=0xc000113fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000113fe8 sp=0xc000113fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 10 gp=0xc0003f68c0 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb50cdfab8?, 0x3?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000489f38 sp=0xc000489f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc000489fc8 sp=0xc000489f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000489fe0 sp=0xc000489fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000489fe8 sp=0xc000489fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 19 gp=0xc0004841c0 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb50cdfab8?, 0x1?, 0xa4?, 0x42?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 35 gp=0xc000106380 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb50cdfab8?, 0x3?, 0x68?, 0x22?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000115f38 sp=0xc000115f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc000115fc8 sp=0xc000115f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000115fe0 sp=0xc000115fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000115fe8 sp=0xc000115fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 36 gp=0xc000106540 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb50cdfab8?, 0x1?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00010ff38 sp=0xc00010ff18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc00010ffc8 sp=0xc00010ff38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00010ffe0 sp=0xc00010ffc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00010ffe8 sp=0xc00010ffe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 11 gp=0xc0003f6a80 m=nil [GC worker (idle)]:
runtime.gopark(0x7ff63aa80160?, 0x1?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000473f38 sp=0xc000473f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc000473fc8 sp=0xc000473f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000473fe0 sp=0xc000473fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000473fe8 sp=0xc000473fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 20 gp=0xc000484380 m=nil [GC worker (idle)]:
runtime.gopark(0x7ff63aa80160?, 0x1?, 0x70?, 0x65?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00046ff38 sp=0xc00046ff18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc00046ffc8 sp=0xc00046ff38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00046ffe0 sp=0xc00046ffc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00046ffe8 sp=0xc00046ffe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 37 gp=0xc000106700 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb4f4edbd0?, 0x1?, 0x64?, 0x83?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000111f38 sp=0xc000111f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc000111fc8 sp=0xc000111f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000111fe0 sp=0xc000111fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000111fe8 sp=0xc000111fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 38 gp=0xc0001068c0 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb50dd3d5c?, 0x3?, 0x8?, 0x43?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00011bf38 sp=0xc00011bf18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc00011bfc8 sp=0xc00011bf38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00011bfe0 sp=0xc00011bfc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00011bfe8 sp=0xc00011bfe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 39 gp=0xc000106a80 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb4f4edbd0?, 0x3?, 0xc8?, 0x1b?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00011df38 sp=0xc00011df18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc00011dfc8 sp=0xc00011df38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00011dfe0 sp=0xc00011dfc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00011dfe8 sp=0xc00011dfe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 12 gp=0xc0003f6c40 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb50cdfab8?, 0x1?, 0x20?, 0x8c?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000475f38 sp=0xc000475f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc000475fc8 sp=0xc000475f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000475fe0 sp=0xc000475fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000475fe8 sp=0xc000475fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 13 gp=0xc0003f6e00 m=nil [GC worker (idle)]:
runtime.gopark(0x4bb50cdfab8?, 0x3?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000117f38 sp=0xc000117f18 pc=0x7ff638ae598e
runtime.gcBgMarkWorker(0xc00003b7a0)
runtime/mgc.go:1423 +0xe9 fp=0xc000117fc8 sp=0xc000117f38 pc=0x7ff638a947a9
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000117fe0 sp=0xc000117fc8 pc=0x7ff638a94685
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000117fe8 sp=0xc000117fe0 pc=0x7ff638aed8e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 15 gp=0xc000506a80 m=nil [select]:
runtime.gopark(0xc000049a08?, 0x2?, 0x0?, 0x0?, 0xc00004986c?)
runtime/proc.go:435 +0xce fp=0xc000049698 sp=0xc000049678 pc=0x7ff638ae598e
runtime.selectgo(0xc000049a08, 0xc000049868, 0x141?, 0x0, 0x1?, 0x1)
runtime/select.go:351 +0x837 fp=0xc0000497d0 sp=0xc000049698 pc=0x7ff638ac6437
github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc000202f00, {0x7ff63a05f690, 0xc0001341c0}, 0xc000692500)
github.com/ollama/ollama/runner/ollamarunner/runner.go:950 +0xc4e fp=0xc000049ac0 sp=0xc0000497d0 pc=0x7ff63901ac2e
github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x7ff63a05f690?, 0xc0001341c0?}, 0xc000049b40?)
:1 +0x36 fp=0xc000049af0 sp=0xc000049ac0 pc=0x7ff6390200f6
net/http.HandlerFunc.ServeHTTP(0xc0006815c0?, {0x7ff63a05f690?, 0xc0001341c0?}, 0xc000049b60?)
net/http/server.go:2294 +0x29 fp=0xc000049b18 sp=0xc000049af0 pc=0x7ff638df51a9
net/http.(*ServeMux).ServeHTTP(0x7ff638a8b785?, {0x7ff63a05f690, 0xc0001341c0}, 0xc000692500)
net/http/server.go:2822 +0x1c4 fp=0xc000049b68 sp=0xc000049b18 pc=0x7ff638df70a4
net/http.serverHandler.ServeHTTP({0x7ff63a05bc30?}, {0x7ff63a05f690?, 0xc0001341c0?}, 0x1?)
net/http/server.go:3301 +0x8e fp=0xc000049b98 sp=0xc000049b68 pc=0x7ff638e14b2e
net/http.(*conn).serve(0xc0006ae3f0, {0x7ff63a061ad8, 0xc000252030})
net/http/server.go:2102 +0x625 fp=0xc000049fb8 sp=0xc000049b98 pc=0x7ff638df36a5
net/http.(*Server).Serve.gowrap3()
net/http/server.go:3454 +0x28 fp=0xc000049fe0 sp=0xc000049fb8 pc=0x7ff638df8f68
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x7ff638aed8e1
created by net/http.(*Server).Serve in goroutine 1
net/http/server.go:3454 +0x485

goroutine 955 gp=0xc0004856c0 m=nil [IO wait]:
runtime.gopark(0x0?, 0xc00068d6a0?, 0x48?, 0xd7?, 0xc00068d74c?)
runtime/proc.go:435 +0xce fp=0xc0004bdd58 sp=0xc0004bdd38 pc=0x7ff638ae598e
runtime.netpollblock(0x1d0?, 0x38a80406?, 0xf6?)
runtime/netpoll.go:575 +0xf7 fp=0xc0004bdd90 sp=0xc0004bdd58 pc=0x7ff638aabdf7
internal/poll.runtime_pollWait(0x220619a6c58, 0x72)
runtime/netpoll.go:351 +0x85 fp=0xc0004bddb0 sp=0xc0004bdd90 pc=0x7ff638ae4b25
internal/poll.(*pollDesc).wait(0x1d0?, 0x72?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0004bddd8 sp=0xc0004bddb0 pc=0x7ff638b7bda7
internal/poll.execIO(0xc00068d6a0, 0x7ff639eea258)
internal/poll/fd_windows.go:177 +0x105 fp=0xc0004bde50 sp=0xc0004bddd8 pc=0x7ff638b7d205
internal/poll.(*FD).Read(0xc00068d688, {0xc0003340a1, 0x1, 0x1})
internal/poll/fd_windows.go:438 +0x29b fp=0xc0004bdef0 sp=0xc0004bde50 pc=0x7ff638b7dedb
net.(*netFD).Read(0xc00068d688, {0xc0003340a1?, 0xc0000c0098?, 0xc0004bdf70?})
net/fd_posix.go:55 +0x25 fp=0xc0004bdf38 sp=0xc0004bdef0 pc=0x7ff638bf1145
net.(*conn).Read(0xc00007c928, {0xc0003340a1?, 0xc0000c0000?, 0x7ff638e65580?})
net/net.go:194 +0x45 fp=0xc0004bdf80 sp=0xc0004bdf38 pc=0x7ff638c00625
net/http.(*connReader).backgroundRead(0xc000334090)
net/http/server.go:690 +0x37 fp=0xc0004bdfc8 sp=0xc0004bdf80 pc=0x7ff638ded577
net/http.(*connReader).startBackgroundRead.gowrap2()
net/http/server.go:686 +0x25 fp=0xc0004bdfe0 sp=0xc0004bdfc8 pc=0x7ff638ded4a5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bdfe8 sp=0xc0004bdfe0 pc=0x7ff638aed8e1
created by net/http.(*connReader).startBackgroundRead in goroutine 15
net/http/server.go:686 +0xb6
rax 0x0
rbx 0x3bbb9ff8d8
rcx 0x0
rdx 0x2205c240000
rdi 0xe06d7363
rsi 0x1
rbp 0x4
rsp 0x3bbb9ff7b0
r8 0x1
r9 0xe06d7363
r10 0x0
r11 0x80000
r12 0x0
r13 0x7ff63a96b780
r14 0xc0005068c0
r15 0x0
rip 0x7ff845f2782a
rflags 0x202
cs 0x33
fs 0x53
gs 0x2b
time=2025-12-30T13:48:28.253+08:00 level=ERROR source=server.go:1583 msg="post predict" error="Post "http://127.0.0.1:55854/completion": read tcp 127.0.0.1:55858->127.0.0.1:55854: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2025/12/30 - 13:48:28 | 500 | 5.6465816s | 127.0.0.1 | POST "/api/chat"

Relevant log output


OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @crackerfly on GitHub (Dec 30, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13585 ### What is the issue? time=2025-12-30T13:16:36.224+08:00 level=INFO source=routes.go:1554 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES:0 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:20m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Program Files\\StarSoftComm\\ZhanAI\\Ollama\\Models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES:]" time=2025-12-30T13:16:36.231+08:00 level=INFO source=images.go:493 msg="total blobs: 20" time=2025-12-30T13:16:36.231+08:00 level=INFO source=images.go:500 msg="total unused blobs removed: 0" time=2025-12-30T13:16:36.232+08:00 level=INFO source=routes.go:1607 msg="Listening on 127.0.0.1:11434 (version 0.13.5)" time=2025-12-30T13:16:36.232+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-12-30T13:16:36.233+08:00 level=WARN source=runner.go:485 msg="user overrode visible devices" GGML_VK_VISIBLE_DEVICES=0 time=2025-12-30T13:16:36.234+08:00 level=WARN source=runner.go:489 msg="if GPUs are not correctly discovered, unset and try again" time=2025-12-30T13:16:36.238+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Program Files\\StarSoftComm\\ZhanAI\\Ollama\\Apps\\Intel\\ollama.exe runner --ollama-engine --port 51381" time=2025-12-30T13:16:36.664+08:00 level=INFO source=types.go:42 msg="inference compute" id=8680517d-0300-0000-0002-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="Intel(R) Arc(TM) 140T GPU (16GB)" libdirs=ollama,vulkan driver=0.0 pci_id="" type=iGPU total="18.0 GiB" available="17.1 GiB" time=2025-12-30T13:16:36.665+08:00 level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="18.0 GiB" threshold="20.0 GiB" [GIN] 2025/12/30 - 13:17:02 | 200 | 0s | 127.0.0.1 | HEAD "/" time=2025-12-30T13:17:05.997+08:00 level=INFO source=download.go:177 msg="downloading ed12a4674d72 in 16 383 MB part(s)" [GIN] 2025/12/30 - 13:42:07 | 200 | 25m5s | 127.0.0.1 | POST "/api/pull" [GIN] 2025/12/30 - 13:42:10 | 200 | 0s | 127.0.0.1 | HEAD "/" time=2025-12-30T13:42:12.169+08:00 level=INFO source=download.go:177 msg="downloading ed12a4674d72 in 16 383 MB part(s)" time=2025-12-30T13:44:10.827+08:00 level=INFO source=download.go:177 msg="downloading 17e666fbe4f4 in 1 551 B part(s)" [GIN] 2025/12/30 - 13:44:16 | 200 | 2m6s | 127.0.0.1 | POST "/api/pull" [GIN] 2025/12/30 - 13:46:52 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/12/30 - 13:46:53 | 200 | 407.5252ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/12/30 - 13:46:53 | 200 | 29.2071ms | 127.0.0.1 | POST "/api/show" time=2025-12-30T13:46:53.126+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Program Files\\StarSoftComm\\ZhanAI\\Ollama\\Apps\\Intel\\ollama.exe runner --ollama-engine --port 55745" time=2025-12-30T13:46:54.259+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2025-12-30T13:46:54.259+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-12-30T13:46:54.260+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=16 efficiency=10 threads=16 time=2025-12-30T13:46:54.302+08:00 level=INFO source=server.go:245 msg="enabling flash attention" time=2025-12-30T13:46:54.303+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Program Files\\StarSoftComm\\ZhanAI\\Ollama\\Apps\\Intel\\ollama.exe runner --ollama-engine --model C:\\Program Files\\StarSoftComm\\ZhanAI\\Ollama\\Models\\blobs\\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 --port 55753" time=2025-12-30T13:46:54.305+08:00 level=INFO source=sched.go:443 msg="system memory" total="31.4 GiB" free="21.4 GiB" free_swap="20.7 GiB" time=2025-12-30T13:46:54.305+08:00 level=INFO source=sched.go:450 msg="gpu memory" id=8680517d-0300-0000-0002-000000000000 library=Vulkan available="16.6 GiB" free="17.1 GiB" minimum="457.0 MiB" overhead="0 B" time=2025-12-30T13:46:54.306+08:00 level=INFO source=server.go:746 msg="loading model" "model layers"=37 requested=-1 time=2025-12-30T13:46:54.332+08:00 level=INFO source=runner.go:1405 msg="starting ollama engine" time=2025-12-30T13:46:54.336+08:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:55753" time=2025-12-30T13:46:54.339+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-12-30T13:46:54.357+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=858 num_key_values=40 load_backend: loaded CPU backend from C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\lib\ollama\ggml-cpu-alderlake.dll ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = Intel(R) Arc(TM) 140T GPU (16GB) (Intel Corporation) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none load_backend: loaded Vulkan backend from C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\lib\ollama\vulkan\ggml-vulkan.dll time=2025-12-30T13:46:54.475+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000 ggml_backend_vk_get_device_memory called: luid 0x0000000000013dcd ggml_dxgi_pdh_init called DXGI + PDH Initialized. Getting GPU free memory info [DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (16GB), LUID: 0x0000000000013DCD, Dedicated: 0.12 GB, Shared: 17.92 GB [DXGI] Adapter Description: NVIDIA RTX PRO 500 Blackwell Generation Laptop GPU, LUID: 0x00000000000142D5, Dedicated: 5.65 GB, Shared: 17.92 GB [DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000014242, Dedicated: 0.00 GB, Shared: 17.92 GB Integrated GPU (Intel(R) Arc(TM) 140T GPU (16GB)) with LUID 0x0000000000013dcd detected. Shared Total: 19238452346.00 bytes (17.92 GB), Shared Usage: 1031168000.00 bytes (0.96 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB) ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 18341502074 total: 19372670074 time=2025-12-30T13:46:54.828+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000 ggml_backend_vk_get_device_memory called: luid 0x0000000000013dcd ggml_dxgi_pdh_init called DXGI + PDH Initialized. Getting GPU free memory info [DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (16GB), LUID: 0x0000000000013DCD, Dedicated: 0.12 GB, Shared: 17.92 GB [DXGI] Adapter Description: NVIDIA RTX PRO 500 Blackwell Generation Laptop GPU, LUID: 0x00000000000142D5, Dedicated: 5.65 GB, Shared: 17.92 GB [DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000014242, Dedicated: 0.00 GB, Shared: 17.92 GB Integrated GPU (Intel(R) Arc(TM) 140T GPU (16GB)) with LUID 0x0000000000013dcd detected. Shared Total: 19238452346.00 bytes (17.92 GB), Shared Usage: 1031168000.00 bytes (0.96 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB) ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 18341502074 total: 19372670074 time=2025-12-30T13:46:55.439+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-12-30T13:46:55.439+08:00 level=INFO source=ggml.go:482 msg="offloading 36 repeating layers to GPU" time=2025-12-30T13:46:55.439+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2025-12-30T13:46:55.439+08:00 level=INFO source=ggml.go:494 msg="offloaded 37/37 layers to GPU" time=2025-12-30T13:46:55.439+08:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="5.4 GiB" time=2025-12-30T13:46:55.440+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="333.8 MiB" time=2025-12-30T13:46:55.440+08:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="576.0 MiB" time=2025-12-30T13:46:55.440+08:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="490.7 MiB" time=2025-12-30T13:46:55.440+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="63.3 MiB" time=2025-12-30T13:46:55.440+08:00 level=INFO source=device.go:272 msg="total memory" size="6.8 GiB" time=2025-12-30T13:46:55.440+08:00 level=INFO source=sched.go:517 msg="loaded runners" count=1 time=2025-12-30T13:46:55.440+08:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding" time=2025-12-30T13:46:55.440+08:00 level=INFO source=server.go:1372 msg="waiting for server to become available" status="llm server loading model" time=2025-12-30T13:47:01.696+08:00 level=INFO source=server.go:1376 msg="llama runner started in 7.39 seconds" [GIN] 2025/12/30 - 13:47:01 | 200 | 8.6300157s | 127.0.0.1 | POST "/api/generate" Exception 0xe06d7363 0x19930520 0xfec79ff980 0x7ff845f2782a PC=0x7ff845f2782a signal arrived during external code execution runtime.cgocall(0x7ff63984b300, 0xc0004715a8) runtime/cgocall.go:167 +0x3e fp=0xc000471580 sp=0xc000471518 pc=0x7ff638ae243e github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_synchronize(0x2f9f30afcf0) _cgo_gotypes.go:1035 +0x45 fp=0xc0004715a8 sp=0xc000471580 pc=0x7ff638f30a45 github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func4.1(...) github.com/ollama/ollama/ml/backend/ggml/ggml.go:833 github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func4() github.com/ollama/ollama/ml/backend/ggml/ggml.go:833 +0x55 fp=0xc0004715f0 sp=0xc0004715a8 pc=0x7ff638f3eed5 github.com/ollama/ollama/ml/backend/ggml.(*Tensor).Floats(0xc008242570) github.com/ollama/ollama/ml/backend/ggml/ggml.go:1065 +0xac fp=0xc000471678 sp=0xc0004715f0 pc=0x7ff638f40e8c github.com/ollama/ollama/runner/ollamarunner.multimodalStore.getTensor(0x7ff639cb21a0?, {0x7ff63a068050, 0xc0000cd760}, {0x7ff63a06d2a0, 0xc000644500}, {0x7ff63a079f68, 0xc008242570}, 0x0) github.com/ollama/ollama/runner/ollamarunner/multimodal.go:97 +0x38e fp=0xc000471788 sp=0xc000471678 pc=0x7ff6390147ae github.com/ollama/ollama/runner/ollamarunner.multimodalStore.getMultimodal(0xc0005899e0, {0x7ff63a068050, 0xc0000cd760}, {0x7ff63a06d2a0, 0xc000644500}, {0xc000050100, 0x4, 0x0?}, 0x0) github.com/ollama/ollama/runner/ollamarunner/multimodal.go:56 +0xe5 fp=0xc0004717f0 sp=0xc000471788 pc=0x7ff639014305 github.com/ollama/ollama/runner/ollamarunner.(*Server).forwardBatch(_, {0x0, {0x0, 0x0}, {0x0, 0x0}, {0x0, 0x0, 0x0}, {{0x0, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:584 +0x1217 fp=0xc000471b58 sp=0xc0004717f0 pc=0x7ff639017977 github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc000202b40, {0x7ff63a061b10, 0xc00059f7c0}) github.com/ollama/ollama/runner/ollamarunner/runner.go:452 +0x18c fp=0xc000471fb8 sp=0xc000471b58 pc=0x7ff63901650c github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1() github.com/ollama/ollama/runner/ollamarunner/runner.go:1418 +0x28 fp=0xc000471fe0 sp=0xc000471fb8 pc=0x7ff63901fc08 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000471fe8 sp=0xc000471fe0 pc=0x7ff638aed8e1 created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/ollamarunner/runner.go:1418 +0x4c9 goroutine 1 gp=0xc0000021c0 m=nil [IO wait]: runtime.gopark(0x7ff638aef0e0?, 0x7ff63aa0ab80?, 0xa0?, 0xb1?, 0xc00064b24c?) runtime/proc.go:435 +0xce fp=0xc000131648 sp=0xc000131628 pc=0x7ff638ae598e runtime.netpollblock(0x224?, 0x38a80406?, 0xf6?) runtime/netpoll.go:575 +0xf7 fp=0xc000131680 sp=0xc000131648 pc=0x7ff638aabdf7 internal/poll.runtime_pollWait(0x2f9ebe7d130, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0001316a0 sp=0xc000131680 pc=0x7ff638ae4b25 internal/poll.(*pollDesc).wait(0x7ff638b7a7b3?, 0x0?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0001316c8 sp=0xc0001316a0 pc=0x7ff638b7bda7 internal/poll.execIO(0xc00064b1a0, 0xc00011f770) internal/poll/fd_windows.go:177 +0x105 fp=0xc000131740 sp=0xc0001316c8 pc=0x7ff638b7d205 internal/poll.(*FD).acceptOne(0xc00064b188, 0x234, {0xc0006760f0?, 0xc00011f7d0?, 0x7ff638b84ec5?}, 0xc00011f804?) internal/poll/fd_windows.go:946 +0x65 fp=0xc0001317a0 sp=0xc000131740 pc=0x7ff638b81785 internal/poll.(*FD).Accept(0xc00064b188, 0xc000131950) internal/poll/fd_windows.go:980 +0x1b6 fp=0xc000131858 sp=0xc0001317a0 pc=0x7ff638b81ab6 net.(*netFD).accept(0xc00064b188) net/fd_windows.go:182 +0x4b fp=0xc000131970 sp=0xc000131858 pc=0x7ff638bf302b net.(*TCPListener).accept(0xc00059db00) net/tcpsock_posix.go:159 +0x1b fp=0xc0001319c0 sp=0xc000131970 pc=0x7ff638c0907b net.(*TCPListener).Accept(0xc00059db00) net/tcpsock.go:380 +0x30 fp=0xc0001319f0 sp=0xc0001319c0 pc=0x7ff638c07e30 net/http.(*onceCloseListener).Accept(0xc00065c3f0?) <autogenerated>:1 +0x24 fp=0xc000131a08 sp=0xc0001319f0 pc=0x7ff638e212a4 net/http.(*Server).Serve(0xc000117000, {0x7ff63a05f4e0, 0xc00059db00}) net/http/server.go:3424 +0x30c fp=0xc000131b38 sp=0xc000131a08 pc=0x7ff638df8b6c github.com/ollama/ollama/runner/ollamarunner.Execute({0xc0000500b0, 0x4, 0x5}) github.com/ollama/ollama/runner/ollamarunner/runner.go:1441 +0x94e fp=0xc000131d08 sp=0xc000131b38 pc=0x7ff63901f98e github.com/ollama/ollama/runner.Execute({0xc000050090?, 0x0?, 0x0?}) github.com/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc000131d30 sp=0xc000131d08 pc=0x7ff639020289 github.com/ollama/ollama/cmd.NewCLI.func2(0xc000116d00?, {0x7ff639e713ff?, 0x4?, 0x7ff639e71403?}) github.com/ollama/ollama/cmd/cmd.go:1841 +0x45 fp=0xc000131d58 sp=0xc000131d30 pc=0x7ff6397ddb45 github.com/spf13/cobra.(*Command).execute(0xc000469b08, {0xc00059f720, 0x5, 0x5}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000131e78 sp=0xc000131d58 pc=0x7ff638c6dafc github.com/spf13/cobra.(*Command).ExecuteC(0xc0005c4608) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000131f30 sp=0xc000131e78 pc=0x7ff638c6e345 github.com/spf13/cobra.(*Command).Execute(...) github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) github.com/spf13/cobra@v1.7.0/command.go:985 main.main() github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000131f50 sp=0xc000131f30 pc=0x7ff6397de62d runtime.main() runtime/proc.go:283 +0x27d fp=0xc000131fe0 sp=0xc000131f50 pc=0x7ff638ab4ddd runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000131fe8 sp=0xc000131fe0 pc=0x7ff638aed8e1 goroutine 2 gp=0xc0000028c0 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000081fa8 sp=0xc000081f88 pc=0x7ff638ae598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.forcegchelper() runtime/proc.go:348 +0xb8 fp=0xc000081fe0 sp=0xc000081fa8 pc=0x7ff638ab50f8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff638aed8e1 created by runtime.init.7 in goroutine 1 runtime/proc.go:336 +0x1a goroutine 3 gp=0xc000002c40 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000083f80 sp=0xc000083f60 pc=0x7ff638ae598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.bgsweep(0xc00008c000) runtime/mgcsweep.go:316 +0xdf fp=0xc000083fc8 sp=0xc000083f80 pc=0x7ff638a9debf runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff638a92285 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff638aed8e1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000002e00 m=nil [GC scavenge wait]: runtime.gopark(0x3a2528?, 0x4c3beb?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000093f78 sp=0xc000093f58 pc=0x7ff638ae598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.(*scavengerState).park(0x7ff63aa31580) runtime/mgcscavenge.go:425 +0x49 fp=0xc000093fa8 sp=0xc000093f78 pc=0x7ff638a9b909 runtime.bgscavenge(0xc00008c000) runtime/mgcscavenge.go:658 +0x59 fp=0xc000093fc8 sp=0xc000093fa8 pc=0x7ff638a9be99 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc000093fe0 sp=0xc000093fc8 pc=0x7ff638a92225 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000093fe8 sp=0xc000093fe0 pc=0x7ff638aed8e1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 5 gp=0xc000003340 m=nil [finalizer wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000095e30 sp=0xc000095e10 pc=0x7ff638ae598e runtime.runfinq() runtime/mfinal.go:196 +0x107 fp=0xc000095fe0 sp=0xc000095e30 pc=0x7ff638a91207 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000095fe8 sp=0xc000095fe0 pc=0x7ff638aed8e1 created by runtime.createfing in goroutine 1 runtime/mfinal.go:166 +0x3d goroutine 6 gp=0xc000003dc0 m=nil [chan receive]: runtime.gopark(0xc0001ff720?, 0xc0082a0060?, 0x60?, 0x5f?, 0x7ff638bdbf68?) runtime/proc.go:435 +0xce fp=0xc000085f18 sp=0xc000085ef8 pc=0x7ff638ae598e runtime.chanrecv(0xc00003a380, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc000085f90 sp=0xc000085f18 pc=0x7ff638a82d45 runtime.chanrecv1(0x7ff638ab4f40?, 0xc000085f76?) runtime/chan.go:506 +0x12 fp=0xc000085fb8 sp=0xc000085f90 pc=0x7ff638a828d2 runtime.unique_runtime_registerUniqueMapCleanup.func2(...) runtime/mgc.go:1796 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1799 +0x2f fp=0xc000085fe0 sp=0xc000085fb8 pc=0x7ff638a954af runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff638aed8e1 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1794 +0x85 goroutine 7 gp=0xc0003f6380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00008ff38 sp=0xc00008ff18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc00008ffc8 sp=0xc00008ff38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00008ffe0 sp=0xc00008ffc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00008ffe8 sp=0xc00008ffe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 18 gp=0xc000484000 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00048bf38 sp=0xc00048bf18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc00048bfc8 sp=0xc00048bf38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00048bfe0 sp=0xc00048bfc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048bfe8 sp=0xc00048bfe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 34 gp=0xc0001061c0 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000487f38 sp=0xc000487f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc000487fc8 sp=0xc000487f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000487fe0 sp=0xc000487fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000487fe8 sp=0xc000487fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 35 gp=0xc000106380 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x3?, 0x80?, 0xf0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000489f38 sp=0xc000489f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc000489fc8 sp=0xc000489f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000489fe0 sp=0xc000489fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000489fe8 sp=0xc000489fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 8 gp=0xc0003f6540 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000091f38 sp=0xc000091f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc000091fc8 sp=0xc000091f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000091fe0 sp=0xc000091fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000091fe8 sp=0xc000091fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 19 gp=0xc0004841c0 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8df8f170?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 36 gp=0xc000106540 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000113f38 sp=0xc000113f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc000113fc8 sp=0xc000113f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000113fe0 sp=0xc000113fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000113fe8 sp=0xc000113fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 9 gp=0xc0003f6700 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8df0f7a4?, 0x1?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00010ff38 sp=0xc00010ff18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc00010ffc8 sp=0xc00010ff38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00010ffe0 sp=0xc00010ffc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00010ffe8 sp=0xc00010ffe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 20 gp=0xc000484380 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x3?, 0x0?, 0x1b?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000495f38 sp=0xc000495f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc000495fc8 sp=0xc000495f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000495fe0 sp=0xc000495fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000495fe8 sp=0xc000495fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 37 gp=0xc000106700 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x1?, 0xa0?, 0xc6?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000115f38 sp=0xc000115f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc000115fc8 sp=0xc000115f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000115fe0 sp=0xc000115fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000115fe8 sp=0xc000115fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 10 gp=0xc0003f68c0 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x1?, 0xcc?, 0xa3?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000111f38 sp=0xc000111f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc000111fc8 sp=0xc000111f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000111fe0 sp=0xc000111fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000111fe8 sp=0xc000111fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 21 gp=0xc000484540 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000497f38 sp=0xc000497f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc000497fc8 sp=0xc000497f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000497fe0 sp=0xc000497fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000497fe8 sp=0xc000497fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 38 gp=0xc0001068c0 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x1?, 0x64?, 0xfe?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000491f38 sp=0xc000491f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc000491fc8 sp=0xc000491f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000491fe0 sp=0xc000491fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000491fe8 sp=0xc000491fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 11 gp=0xc0003f6a80 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8ddbe6ac?, 0x1?, 0xc8?, 0x13?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000473f38 sp=0xc000473f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc000473fc8 sp=0xc000473f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000473fe0 sp=0xc000473fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000473fe8 sp=0xc000473fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 22 gp=0xc000484700 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00046ff38 sp=0xc00046ff18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc00046ffc8 sp=0xc00046ff38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00046ffe0 sp=0xc00046ffc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00046ffe8 sp=0xc00046ffe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 39 gp=0xc000106a80 m=nil [GC worker (idle)]: runtime.gopark(0x4ae8de0d20c?, 0x3?, 0x44?, 0x14?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000493f38 sp=0xc000493f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b960) runtime/mgc.go:1423 +0xe9 fp=0xc000493fc8 sp=0xc000493f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000493fe0 sp=0xc000493fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000493fe8 sp=0xc000493fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 13 gp=0xc000107180 m=nil [select]: runtime.gopark(0xc000049a08?, 0x2?, 0x0?, 0x91?, 0xc00004986c?) runtime/proc.go:435 +0xce fp=0xc000049698 sp=0xc000049678 pc=0x7ff638ae598e runtime.selectgo(0xc000049a08, 0xc000049868, 0x141?, 0x0, 0x1?, 0x1) runtime/select.go:351 +0x837 fp=0xc0000497d0 sp=0xc000049698 pc=0x7ff638ac6437 github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc000202b40, {0x7ff63a05f690, 0xc00039c000}, 0xc0003643c0) github.com/ollama/ollama/runner/ollamarunner/runner.go:950 +0xc4e fp=0xc000049ac0 sp=0xc0000497d0 pc=0x7ff63901ac2e github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x7ff63a05f690?, 0xc00039c000?}, 0xc000049b40?) <autogenerated>:1 +0x36 fp=0xc000049af0 sp=0xc000049ac0 pc=0x7ff6390200f6 net/http.HandlerFunc.ServeHTTP(0xc0005aed80?, {0x7ff63a05f690?, 0xc00039c000?}, 0xc000049b60?) net/http/server.go:2294 +0x29 fp=0xc000049b18 sp=0xc000049af0 pc=0x7ff638df51a9 net/http.(*ServeMux).ServeHTTP(0x7ff638a8b785?, {0x7ff63a05f690, 0xc00039c000}, 0xc0003643c0) net/http/server.go:2822 +0x1c4 fp=0xc000049b68 sp=0xc000049b18 pc=0x7ff638df70a4 net/http.serverHandler.ServeHTTP({0x7ff63a05bc30?}, {0x7ff63a05f690?, 0xc00039c000?}, 0x1?) net/http/server.go:3301 +0x8e fp=0xc000049b98 sp=0xc000049b68 pc=0x7ff638e14b2e net/http.(*conn).serve(0xc00065c3f0, {0x7ff63a061ad8, 0xc000252f90}) net/http/server.go:2102 +0x625 fp=0xc000049fb8 sp=0xc000049b98 pc=0x7ff638df36a5 net/http.(*Server).Serve.gowrap3() net/http/server.go:3454 +0x28 fp=0xc000049fe0 sp=0xc000049fb8 pc=0x7ff638df8f68 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x7ff638aed8e1 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3454 +0x485 goroutine 911 gp=0xc0005ca380 m=nil [IO wait]: runtime.gopark(0x0?, 0xc00064b420?, 0xc8?, 0xb4?, 0xc00064b4cc?) runtime/proc.go:435 +0xce fp=0xc000575d58 sp=0xc000575d38 pc=0x7ff638ae598e runtime.netpollblock(0x214?, 0x38a80406?, 0xf6?) runtime/netpoll.go:575 +0xf7 fp=0xc000575d90 sp=0xc000575d58 pc=0x7ff638aabdf7 internal/poll.runtime_pollWait(0x2f9ebe7d018, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc000575db0 sp=0xc000575d90 pc=0x7ff638ae4b25 internal/poll.(*pollDesc).wait(0x214?, 0x72?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000575dd8 sp=0xc000575db0 pc=0x7ff638b7bda7 internal/poll.execIO(0xc00064b420, 0x7ff639eea258) internal/poll/fd_windows.go:177 +0x105 fp=0xc000575e50 sp=0xc000575dd8 pc=0x7ff638b7d205 internal/poll.(*FD).Read(0xc00064b408, {0xc0003340a1, 0x1, 0x1}) internal/poll/fd_windows.go:438 +0x29b fp=0xc000575ef0 sp=0xc000575e50 pc=0x7ff638b7dedb net.(*netFD).Read(0xc00064b408, {0xc0003340a1?, 0xc000644298?, 0xc000575f70?}) net/fd_posix.go:55 +0x25 fp=0xc000575f38 sp=0xc000575ef0 pc=0x7ff638bf1145 net.(*conn).Read(0xc0005963d8, {0xc0003340a1?, 0xff000000ff000000?, 0xff000000ff000000?}) net/net.go:194 +0x45 fp=0xc000575f80 sp=0xc000575f38 pc=0x7ff638c00625 net/http.(*connReader).backgroundRead(0xc000334090) net/http/server.go:690 +0x37 fp=0xc000575fc8 sp=0xc000575f80 pc=0x7ff638ded577 net/http.(*connReader).startBackgroundRead.gowrap2() net/http/server.go:686 +0x25 fp=0xc000575fe0 sp=0xc000575fc8 pc=0x7ff638ded4a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000575fe8 sp=0xc000575fe0 pc=0x7ff638aed8e1 created by net/http.(*connReader).startBackgroundRead in goroutine 13 net/http/server.go:686 +0xb6 rax 0x0 rbx 0xfec79ff908 rcx 0x0 rdx 0x2f9e6860000 rdi 0xe06d7363 rsi 0x1 rbp 0x4 rsp 0xfec79ff7e0 r8 0x1 r9 0xe06d7363 r10 0x0 r11 0x90000 r12 0x0 r13 0x7ff63a96b780 r14 0xc000106fc0 r15 0x0 rip 0x7ff845f2782a rflags 0x202 cs 0x33 fs 0x53 gs 0x2b time=2025-12-30T13:47:36.508+08:00 level=ERROR source=server.go:1583 msg="post predict" error="Post \"http://127.0.0.1:55753/completion\": read tcp 127.0.0.1:55757->127.0.0.1:55753: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2025/12/30 - 13:47:36 | 500 | 8.7242091s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/12/30 - 13:48:08 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/12/30 - 13:48:08 | 200 | 29.268ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/12/30 - 13:48:08 | 200 | 28.8107ms | 127.0.0.1 | POST "/api/show" time=2025-12-30T13:48:08.738+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Program Files\\StarSoftComm\\ZhanAI\\Ollama\\Apps\\Intel\\ollama.exe runner --ollama-engine --port 55849" time=2025-12-30T13:48:09.145+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2025-12-30T13:48:09.146+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-12-30T13:48:09.147+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=16 efficiency=10 threads=16 time=2025-12-30T13:48:09.191+08:00 level=INFO source=server.go:245 msg="enabling flash attention" time=2025-12-30T13:48:09.192+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="C:\\Program Files\\StarSoftComm\\ZhanAI\\Ollama\\Apps\\Intel\\ollama.exe runner --ollama-engine --model C:\\Program Files\\StarSoftComm\\ZhanAI\\Ollama\\Models\\blobs\\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 --port 55854" time=2025-12-30T13:48:09.194+08:00 level=INFO source=sched.go:443 msg="system memory" total="31.4 GiB" free="21.6 GiB" free_swap="20.7 GiB" time=2025-12-30T13:48:09.195+08:00 level=INFO source=sched.go:450 msg="gpu memory" id=8680517d-0300-0000-0002-000000000000 library=Vulkan available="16.6 GiB" free="17.0 GiB" minimum="457.0 MiB" overhead="0 B" time=2025-12-30T13:48:09.195+08:00 level=INFO source=server.go:746 msg="loading model" "model layers"=37 requested=-1 time=2025-12-30T13:48:09.222+08:00 level=INFO source=runner.go:1405 msg="starting ollama engine" time=2025-12-30T13:48:09.226+08:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:55854" time=2025-12-30T13:48:09.227+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-12-30T13:48:09.245+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=858 num_key_values=40 load_backend: loaded CPU backend from C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\lib\ollama\ggml-cpu-alderlake.dll ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = Intel(R) Arc(TM) 140T GPU (16GB) (Intel Corporation) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none load_backend: loaded Vulkan backend from C:\Program Files\StarSoftComm\ZhanAI\Ollama\Apps\Intel\lib\ollama\vulkan\ggml-vulkan.dll time=2025-12-30T13:48:09.363+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000 ggml_backend_vk_get_device_memory called: luid 0x0000000000013dcd ggml_dxgi_pdh_init called DXGI + PDH Initialized. Getting GPU free memory info [DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (16GB), LUID: 0x0000000000013DCD, Dedicated: 0.12 GB, Shared: 17.92 GB [DXGI] Adapter Description: NVIDIA RTX PRO 500 Blackwell Generation Laptop GPU, LUID: 0x00000000000142D5, Dedicated: 5.65 GB, Shared: 17.92 GB [DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000014242, Dedicated: 0.00 GB, Shared: 17.92 GB Integrated GPU (Intel(R) Arc(TM) 140T GPU (16GB)) with LUID 0x0000000000013dcd detected. Shared Total: 19238452346.00 bytes (17.92 GB), Shared Usage: 1090072576.00 bytes (1.02 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB) ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 18282597498 total: 19372670074 time=2025-12-30T13:48:09.719+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" ggml_backend_vk_get_device_memory called: uuid 8680517d-0300-0000-0002-000000000000 ggml_backend_vk_get_device_memory called: luid 0x0000000000013dcd ggml_dxgi_pdh_init called DXGI + PDH Initialized. Getting GPU free memory info [DXGI] Adapter Description: Intel(R) Arc(TM) 140T GPU (16GB), LUID: 0x0000000000013DCD, Dedicated: 0.12 GB, Shared: 17.92 GB [DXGI] Adapter Description: NVIDIA RTX PRO 500 Blackwell Generation Laptop GPU, LUID: 0x00000000000142D5, Dedicated: 5.65 GB, Shared: 17.92 GB [DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x0000000000014242, Dedicated: 0.00 GB, Shared: 17.92 GB Integrated GPU (Intel(R) Arc(TM) 140T GPU (16GB)) with LUID 0x0000000000013dcd detected. Shared Total: 19238452346.00 bytes (17.92 GB), Shared Usage: 1090072576.00 bytes (1.02 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB) ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 18282597498 total: 19372670074 time=2025-12-30T13:48:10.277+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:6 GPULayers:37[ID:8680517d-0300-0000-0002-000000000000 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-12-30T13:48:10.277+08:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="5.4 GiB" time=2025-12-30T13:48:10.277+08:00 level=INFO source=ggml.go:482 msg="offloading 36 repeating layers to GPU" time=2025-12-30T13:48:10.277+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2025-12-30T13:48:10.277+08:00 level=INFO source=ggml.go:494 msg="offloaded 37/37 layers to GPU" time=2025-12-30T13:48:10.278+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="333.8 MiB" time=2025-12-30T13:48:10.278+08:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="576.0 MiB" time=2025-12-30T13:48:10.278+08:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="490.7 MiB" time=2025-12-30T13:48:10.278+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="63.3 MiB" time=2025-12-30T13:48:10.278+08:00 level=INFO source=device.go:272 msg="total memory" size="6.8 GiB" time=2025-12-30T13:48:10.278+08:00 level=INFO source=sched.go:517 msg="loaded runners" count=1 time=2025-12-30T13:48:10.278+08:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding" time=2025-12-30T13:48:10.279+08:00 level=INFO source=server.go:1372 msg="waiting for server to become available" status="llm server loading model" time=2025-12-30T13:48:16.538+08:00 level=INFO source=server.go:1376 msg="llama runner started in 7.34 seconds" [GIN] 2025/12/30 - 13:48:16 | 200 | 7.8534757s | 127.0.0.1 | POST "/api/generate" Exception 0xe06d7363 0x19930520 0x3bbb9ff950 0x7ff845f2782a PC=0x7ff845f2782a signal arrived during external code execution runtime.cgocall(0x7ff63984b300, 0xc0004715a8) runtime/cgocall.go:167 +0x3e fp=0xc000471580 sp=0xc000471518 pc=0x7ff638ae243e github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_synchronize(0x22066ef23b0) _cgo_gotypes.go:1035 +0x45 fp=0xc0004715a8 sp=0xc000471580 pc=0x7ff638f30a45 github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func4.1(...) github.com/ollama/ollama/ml/backend/ggml/ggml.go:833 github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func4() github.com/ollama/ollama/ml/backend/ggml/ggml.go:833 +0x55 fp=0xc0004715f0 sp=0xc0004715a8 pc=0x7ff638f3eed5 github.com/ollama/ollama/ml/backend/ggml.(*Tensor).Floats(0xc000f0a600) github.com/ollama/ollama/ml/backend/ggml/ggml.go:1065 +0xac fp=0xc000471678 sp=0xc0004715f0 pc=0x7ff638f40e8c github.com/ollama/ollama/runner/ollamarunner.multimodalStore.getTensor(0x7ff639cb21a0?, {0x7ff63a068050, 0xc0000cd760}, {0x7ff63a06d2a0, 0xc0000c0000}, {0x7ff63a079f68, 0xc000f0a600}, 0x0) github.com/ollama/ollama/runner/ollamarunner/multimodal.go:97 +0x38e fp=0xc000471788 sp=0xc000471678 pc=0x7ff6390147ae github.com/ollama/ollama/runner/ollamarunner.multimodalStore.getMultimodal(0xc00045e9f0, {0x7ff63a068050, 0xc0000cd760}, {0x7ff63a06d2a0, 0xc0000c0000}, {0xc000050100, 0x4, 0x0?}, 0x0) github.com/ollama/ollama/runner/ollamarunner/multimodal.go:56 +0xe5 fp=0xc0004717f0 sp=0xc000471788 pc=0x7ff639014305 github.com/ollama/ollama/runner/ollamarunner.(*Server).forwardBatch(_, {0x0, {0x0, 0x0}, {0x0, 0x0}, {0x0, 0x0, 0x0}, {{0x0, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:584 +0x1217 fp=0xc000471b58 sp=0xc0004717f0 pc=0x7ff639017977 github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc000202f00, {0x7ff63a061b10, 0xc0000ddae0}) github.com/ollama/ollama/runner/ollamarunner/runner.go:452 +0x18c fp=0xc000471fb8 sp=0xc000471b58 pc=0x7ff63901650c github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1() github.com/ollama/ollama/runner/ollamarunner/runner.go:1418 +0x28 fp=0xc000471fe0 sp=0xc000471fb8 pc=0x7ff63901fc08 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000471fe8 sp=0xc000471fe0 pc=0x7ff638aed8e1 created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/ollamarunner/runner.go:1418 +0x4c9 goroutine 1 gp=0xc0000021c0 m=nil [IO wait]: runtime.gopark(0x7ff638aef0e0?, 0x7ff63aa0ab80?, 0x20?, 0xd4?, 0xc00068d4cc?) runtime/proc.go:435 +0xce fp=0xc0006d3648 sp=0xc0006d3628 pc=0x7ff638ae598e runtime.netpollblock(0x1cc?, 0x38a80406?, 0xf6?) runtime/netpoll.go:575 +0xf7 fp=0xc0006d3680 sp=0xc0006d3648 pc=0x7ff638aabdf7 internal/poll.runtime_pollWait(0x220619a6d70, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0006d36a0 sp=0xc0006d3680 pc=0x7ff638ae4b25 internal/poll.(*pollDesc).wait(0x7ff638b7a7b3?, 0x0?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0006d36c8 sp=0xc0006d36a0 pc=0x7ff638b7bda7 internal/poll.execIO(0xc00068d420, 0xc00050f770) internal/poll/fd_windows.go:177 +0x105 fp=0xc0006d3740 sp=0xc0006d36c8 pc=0x7ff638b7d205 internal/poll.(*FD).acceptOne(0xc00068d408, 0x22c, {0xc0006cc0f0?, 0xc00050f7d0?, 0x7ff638b84ec5?}, 0xc00050f804?) internal/poll/fd_windows.go:946 +0x65 fp=0xc0006d37a0 sp=0xc0006d3740 pc=0x7ff638b81785 internal/poll.(*FD).Accept(0xc00068d408, 0xc0006d3950) internal/poll/fd_windows.go:980 +0x1b6 fp=0xc0006d3858 sp=0xc0006d37a0 pc=0x7ff638b81ab6 net.(*netFD).accept(0xc00068d408) net/fd_windows.go:182 +0x4b fp=0xc0006d3970 sp=0xc0006d3858 pc=0x7ff638bf302b net.(*TCPListener).accept(0xc0002c0940) net/tcpsock_posix.go:159 +0x1b fp=0xc0006d39c0 sp=0xc0006d3970 pc=0x7ff638c0907b net.(*TCPListener).Accept(0xc0002c0940) net/tcpsock.go:380 +0x30 fp=0xc0006d39f0 sp=0xc0006d39c0 pc=0x7ff638c07e30 net/http.(*onceCloseListener).Accept(0xc0006ae3f0?) <autogenerated>:1 +0x24 fp=0xc0006d3a08 sp=0xc0006d39f0 pc=0x7ff638e212a4 net/http.(*Server).Serve(0xc0001cd700, {0x7ff63a05f4e0, 0xc0002c0940}) net/http/server.go:3424 +0x30c fp=0xc0006d3b38 sp=0xc0006d3a08 pc=0x7ff638df8b6c github.com/ollama/ollama/runner/ollamarunner.Execute({0xc0000500b0, 0x4, 0x5}) github.com/ollama/ollama/runner/ollamarunner/runner.go:1441 +0x94e fp=0xc0006d3d08 sp=0xc0006d3b38 pc=0x7ff63901f98e github.com/ollama/ollama/runner.Execute({0xc000050090?, 0x0?, 0x0?}) github.com/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc0006d3d30 sp=0xc0006d3d08 pc=0x7ff639020289 github.com/ollama/ollama/cmd.NewCLI.func2(0xc0001cd400?, {0x7ff639e713ff?, 0x4?, 0x7ff639e71403?}) github.com/ollama/ollama/cmd/cmd.go:1841 +0x45 fp=0xc0006d3d58 sp=0xc0006d3d30 pc=0x7ff6397ddb45 github.com/spf13/cobra.(*Command).execute(0xc0006b1508, {0xc0000dda40, 0x5, 0x5}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc0006d3e78 sp=0xc0006d3d58 pc=0x7ff638c6dafc github.com/spf13/cobra.(*Command).ExecuteC(0xc00045af08) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc0006d3f30 sp=0xc0006d3e78 pc=0x7ff638c6e345 github.com/spf13/cobra.(*Command).Execute(...) github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) github.com/spf13/cobra@v1.7.0/command.go:985 main.main() github.com/ollama/ollama/main.go:12 +0x4d fp=0xc0006d3f50 sp=0xc0006d3f30 pc=0x7ff6397de62d runtime.main() runtime/proc.go:283 +0x27d fp=0xc0006d3fe0 sp=0xc0006d3f50 pc=0x7ff638ab4ddd runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0006d3fe8 sp=0xc0006d3fe0 pc=0x7ff638aed8e1 goroutine 2 gp=0xc0000028c0 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000081fa8 sp=0xc000081f88 pc=0x7ff638ae598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.forcegchelper() runtime/proc.go:348 +0xb8 fp=0xc000081fe0 sp=0xc000081fa8 pc=0x7ff638ab50f8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff638aed8e1 created by runtime.init.7 in goroutine 1 runtime/proc.go:336 +0x1a goroutine 3 gp=0xc000002c40 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000083f80 sp=0xc000083f60 pc=0x7ff638ae598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.bgsweep(0xc00008c000) runtime/mgcsweep.go:316 +0xdf fp=0xc000083fc8 sp=0xc000083f80 pc=0x7ff638a9debf runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff638a92285 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff638aed8e1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000002e00 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x4ca3d8?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000093f78 sp=0xc000093f58 pc=0x7ff638ae598e runtime.goparkunlock(...) runtime/proc.go:441 runtime.(*scavengerState).park(0x7ff63aa31580) runtime/mgcscavenge.go:425 +0x49 fp=0xc000093fa8 sp=0xc000093f78 pc=0x7ff638a9b909 runtime.bgscavenge(0xc00008c000) runtime/mgcscavenge.go:658 +0x59 fp=0xc000093fc8 sp=0xc000093fa8 pc=0x7ff638a9be99 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc000093fe0 sp=0xc000093fc8 pc=0x7ff638a92225 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000093fe8 sp=0xc000093fe0 pc=0x7ff638aed8e1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 5 gp=0xc000003340 m=nil [finalizer wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000095e30 sp=0xc000095e10 pc=0x7ff638ae598e runtime.runfinq() runtime/mfinal.go:196 +0x107 fp=0xc000095fe0 sp=0xc000095e30 pc=0x7ff638a91207 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000095fe8 sp=0xc000095fe0 pc=0x7ff638aed8e1 created by runtime.createfing in goroutine 1 runtime/mfinal.go:166 +0x3d goroutine 6 gp=0xc000003dc0 m=nil [chan receive]: runtime.gopark(0xc0001ff720?, 0xc000f0a630?, 0x60?, 0x5f?, 0x7ff638bdbf68?) runtime/proc.go:435 +0xce fp=0xc000085f18 sp=0xc000085ef8 pc=0x7ff638ae598e runtime.chanrecv(0xc00003a380, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc000085f90 sp=0xc000085f18 pc=0x7ff638a82d45 runtime.chanrecv1(0x7ff638ab4f40?, 0xc000085f76?) runtime/chan.go:506 +0x12 fp=0xc000085fb8 sp=0xc000085f90 pc=0x7ff638a828d2 runtime.unique_runtime_registerUniqueMapCleanup.func2(...) runtime/mgc.go:1796 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1799 +0x2f fp=0xc000085fe0 sp=0xc000085fb8 pc=0x7ff638a954af runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff638aed8e1 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1794 +0x85 goroutine 7 gp=0xc0003f6380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00008ff38 sp=0xc00008ff18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00008ffc8 sp=0xc00008ff38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00008ffe0 sp=0xc00008ffc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00008ffe8 sp=0xc00008ffe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 8 gp=0xc0003f6540 m=nil [GC worker (idle)]: runtime.gopark(0x7ff63aa80160?, 0x1?, 0x70?, 0x65?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000091f38 sp=0xc000091f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000091fc8 sp=0xc000091f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000091fe0 sp=0xc000091fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000091fe8 sp=0xc000091fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 18 gp=0xc000484000 m=nil [GC worker (idle)]: runtime.gopark(0x4bb50dd3d5c?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00048bf38 sp=0xc00048bf18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00048bfc8 sp=0xc00048bf38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00048bfe0 sp=0xc00048bfc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048bfe8 sp=0xc00048bfe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 9 gp=0xc0003f6700 m=nil [GC worker (idle)]: runtime.gopark(0x4bb50cdfab8?, 0x3?, 0x70?, 0x65?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000487f38 sp=0xc000487f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000487fc8 sp=0xc000487f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000487fe0 sp=0xc000487fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000487fe8 sp=0xc000487fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 34 gp=0xc0001061c0 m=nil [GC worker (idle)]: runtime.gopark(0x4bb50dd3d5c?, 0x3?, 0x58?, 0x70?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000113f38 sp=0xc000113f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000113fc8 sp=0xc000113f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000113fe0 sp=0xc000113fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000113fe8 sp=0xc000113fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 10 gp=0xc0003f68c0 m=nil [GC worker (idle)]: runtime.gopark(0x4bb50cdfab8?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000489f38 sp=0xc000489f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000489fc8 sp=0xc000489f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000489fe0 sp=0xc000489fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000489fe8 sp=0xc000489fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 19 gp=0xc0004841c0 m=nil [GC worker (idle)]: runtime.gopark(0x4bb50cdfab8?, 0x1?, 0xa4?, 0x42?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 35 gp=0xc000106380 m=nil [GC worker (idle)]: runtime.gopark(0x4bb50cdfab8?, 0x3?, 0x68?, 0x22?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000115f38 sp=0xc000115f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000115fc8 sp=0xc000115f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000115fe0 sp=0xc000115fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000115fe8 sp=0xc000115fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 36 gp=0xc000106540 m=nil [GC worker (idle)]: runtime.gopark(0x4bb50cdfab8?, 0x1?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00010ff38 sp=0xc00010ff18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00010ffc8 sp=0xc00010ff38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00010ffe0 sp=0xc00010ffc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00010ffe8 sp=0xc00010ffe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 11 gp=0xc0003f6a80 m=nil [GC worker (idle)]: runtime.gopark(0x7ff63aa80160?, 0x1?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000473f38 sp=0xc000473f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000473fc8 sp=0xc000473f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000473fe0 sp=0xc000473fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000473fe8 sp=0xc000473fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 20 gp=0xc000484380 m=nil [GC worker (idle)]: runtime.gopark(0x7ff63aa80160?, 0x1?, 0x70?, 0x65?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00046ff38 sp=0xc00046ff18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00046ffc8 sp=0xc00046ff38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00046ffe0 sp=0xc00046ffc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00046ffe8 sp=0xc00046ffe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 37 gp=0xc000106700 m=nil [GC worker (idle)]: runtime.gopark(0x4bb4f4edbd0?, 0x1?, 0x64?, 0x83?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000111f38 sp=0xc000111f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000111fc8 sp=0xc000111f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000111fe0 sp=0xc000111fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000111fe8 sp=0xc000111fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 38 gp=0xc0001068c0 m=nil [GC worker (idle)]: runtime.gopark(0x4bb50dd3d5c?, 0x3?, 0x8?, 0x43?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011bf38 sp=0xc00011bf18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00011bfc8 sp=0xc00011bf38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011bfe0 sp=0xc00011bfc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011bfe8 sp=0xc00011bfe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 39 gp=0xc000106a80 m=nil [GC worker (idle)]: runtime.gopark(0x4bb4f4edbd0?, 0x3?, 0xc8?, 0x1b?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011df38 sp=0xc00011df18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00011dfc8 sp=0xc00011df38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011dfe0 sp=0xc00011dfc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011dfe8 sp=0xc00011dfe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 12 gp=0xc0003f6c40 m=nil [GC worker (idle)]: runtime.gopark(0x4bb50cdfab8?, 0x1?, 0x20?, 0x8c?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000475f38 sp=0xc000475f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000475fc8 sp=0xc000475f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000475fe0 sp=0xc000475fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000475fe8 sp=0xc000475fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 13 gp=0xc0003f6e00 m=nil [GC worker (idle)]: runtime.gopark(0x4bb50cdfab8?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000117f38 sp=0xc000117f18 pc=0x7ff638ae598e runtime.gcBgMarkWorker(0xc00003b7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000117fc8 sp=0xc000117f38 pc=0x7ff638a947a9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000117fe0 sp=0xc000117fc8 pc=0x7ff638a94685 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000117fe8 sp=0xc000117fe0 pc=0x7ff638aed8e1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 15 gp=0xc000506a80 m=nil [select]: runtime.gopark(0xc000049a08?, 0x2?, 0x0?, 0x0?, 0xc00004986c?) runtime/proc.go:435 +0xce fp=0xc000049698 sp=0xc000049678 pc=0x7ff638ae598e runtime.selectgo(0xc000049a08, 0xc000049868, 0x141?, 0x0, 0x1?, 0x1) runtime/select.go:351 +0x837 fp=0xc0000497d0 sp=0xc000049698 pc=0x7ff638ac6437 github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc000202f00, {0x7ff63a05f690, 0xc0001341c0}, 0xc000692500) github.com/ollama/ollama/runner/ollamarunner/runner.go:950 +0xc4e fp=0xc000049ac0 sp=0xc0000497d0 pc=0x7ff63901ac2e github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x7ff63a05f690?, 0xc0001341c0?}, 0xc000049b40?) <autogenerated>:1 +0x36 fp=0xc000049af0 sp=0xc000049ac0 pc=0x7ff6390200f6 net/http.HandlerFunc.ServeHTTP(0xc0006815c0?, {0x7ff63a05f690?, 0xc0001341c0?}, 0xc000049b60?) net/http/server.go:2294 +0x29 fp=0xc000049b18 sp=0xc000049af0 pc=0x7ff638df51a9 net/http.(*ServeMux).ServeHTTP(0x7ff638a8b785?, {0x7ff63a05f690, 0xc0001341c0}, 0xc000692500) net/http/server.go:2822 +0x1c4 fp=0xc000049b68 sp=0xc000049b18 pc=0x7ff638df70a4 net/http.serverHandler.ServeHTTP({0x7ff63a05bc30?}, {0x7ff63a05f690?, 0xc0001341c0?}, 0x1?) net/http/server.go:3301 +0x8e fp=0xc000049b98 sp=0xc000049b68 pc=0x7ff638e14b2e net/http.(*conn).serve(0xc0006ae3f0, {0x7ff63a061ad8, 0xc000252030}) net/http/server.go:2102 +0x625 fp=0xc000049fb8 sp=0xc000049b98 pc=0x7ff638df36a5 net/http.(*Server).Serve.gowrap3() net/http/server.go:3454 +0x28 fp=0xc000049fe0 sp=0xc000049fb8 pc=0x7ff638df8f68 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x7ff638aed8e1 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3454 +0x485 goroutine 955 gp=0xc0004856c0 m=nil [IO wait]: runtime.gopark(0x0?, 0xc00068d6a0?, 0x48?, 0xd7?, 0xc00068d74c?) runtime/proc.go:435 +0xce fp=0xc0004bdd58 sp=0xc0004bdd38 pc=0x7ff638ae598e runtime.netpollblock(0x1d0?, 0x38a80406?, 0xf6?) runtime/netpoll.go:575 +0xf7 fp=0xc0004bdd90 sp=0xc0004bdd58 pc=0x7ff638aabdf7 internal/poll.runtime_pollWait(0x220619a6c58, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0004bddb0 sp=0xc0004bdd90 pc=0x7ff638ae4b25 internal/poll.(*pollDesc).wait(0x1d0?, 0x72?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0004bddd8 sp=0xc0004bddb0 pc=0x7ff638b7bda7 internal/poll.execIO(0xc00068d6a0, 0x7ff639eea258) internal/poll/fd_windows.go:177 +0x105 fp=0xc0004bde50 sp=0xc0004bddd8 pc=0x7ff638b7d205 internal/poll.(*FD).Read(0xc00068d688, {0xc0003340a1, 0x1, 0x1}) internal/poll/fd_windows.go:438 +0x29b fp=0xc0004bdef0 sp=0xc0004bde50 pc=0x7ff638b7dedb net.(*netFD).Read(0xc00068d688, {0xc0003340a1?, 0xc0000c0098?, 0xc0004bdf70?}) net/fd_posix.go:55 +0x25 fp=0xc0004bdf38 sp=0xc0004bdef0 pc=0x7ff638bf1145 net.(*conn).Read(0xc00007c928, {0xc0003340a1?, 0xc0000c0000?, 0x7ff638e65580?}) net/net.go:194 +0x45 fp=0xc0004bdf80 sp=0xc0004bdf38 pc=0x7ff638c00625 net/http.(*connReader).backgroundRead(0xc000334090) net/http/server.go:690 +0x37 fp=0xc0004bdfc8 sp=0xc0004bdf80 pc=0x7ff638ded577 net/http.(*connReader).startBackgroundRead.gowrap2() net/http/server.go:686 +0x25 fp=0xc0004bdfe0 sp=0xc0004bdfc8 pc=0x7ff638ded4a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bdfe8 sp=0xc0004bdfe0 pc=0x7ff638aed8e1 created by net/http.(*connReader).startBackgroundRead in goroutine 15 net/http/server.go:686 +0xb6 rax 0x0 rbx 0x3bbb9ff8d8 rcx 0x0 rdx 0x2205c240000 rdi 0xe06d7363 rsi 0x1 rbp 0x4 rsp 0x3bbb9ff7b0 r8 0x1 r9 0xe06d7363 r10 0x0 r11 0x80000 r12 0x0 r13 0x7ff63a96b780 r14 0xc0005068c0 r15 0x0 rip 0x7ff845f2782a rflags 0x202 cs 0x33 fs 0x53 gs 0x2b time=2025-12-30T13:48:28.253+08:00 level=ERROR source=server.go:1583 msg="post predict" error="Post \"http://127.0.0.1:55854/completion\": read tcp 127.0.0.1:55858->127.0.0.1:55854: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2025/12/30 - 13:48:28 | 500 | 5.6465816s | 127.0.0.1 | POST "/api/chat" ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 21:45:54 -05:00
Author
Owner

@D337z commented on GitHub (Dec 31, 2025):

This looks like it's the same error as this one: https://github.com/ollama/ollama/issues/13573
The issue seems to stem from how Vulkan is being used. When this was attempted to be reproduced, the person reproducing it attempted it with an AMD GPU which is already supported via ROCm even though this error seems to pertain to Intel GPUs specifically which are only supported via Vulkan (or openVINO if you modified the source to support it and use VINO models).
While I'm glad that Intel is attempting to be supported via Vulkan, I believe that the support is buggier than if it has been incorporated in via OneAPI instead.

<!-- gh-comment-id:3702701111 --> @D337z commented on GitHub (Dec 31, 2025): This looks like it's the same error as this one: https://github.com/ollama/ollama/issues/13573 The issue seems to stem from how Vulkan is being used. When this was attempted to be reproduced, the person reproducing it attempted it with an AMD GPU which is already supported via ROCm even though this error seems to pertain to Intel GPUs specifically which are only supported via Vulkan (or openVINO if you modified the source to support it and use VINO models). While I'm glad that Intel is attempting to be supported via Vulkan, I believe that the support is buggier than if it has been incorporated in via OneAPI instead.
Author
Owner

@cluick commented on GitHub (Jan 14, 2026):

This looks like it's the same error as this one: #13573 The issue seems to stem from how Vulkan is being used. When this was attempted to be reproduced, the person reproducing it attempted it with an AMD GPU which is already supported via ROCm even though this error seems to pertain to Intel GPUs specifically which are only supported via Vulkan (or openVINO if you modified the source to support it and use VINO models). While I'm glad that Intel is attempting to be supported via Vulkan, I believe that the support is buggier than if it has been incorporated in via OneAPI instead.

I guess you are right. I receive the same error when trying to call /api/embed on the bge-m3:latest model in Ollama 0.14.0 with Vulkan support enabled. I'm using an embedded Intel Iris XE GPU. Here is my error log:

ollama-0.14.0_bge-m3_embed.error.txt

<!-- gh-comment-id:3751886592 --> @cluick commented on GitHub (Jan 14, 2026): > This looks like it's the same error as this one: [#13573](https://github.com/ollama/ollama/issues/13573) The issue seems to stem from how Vulkan is being used. When this was attempted to be reproduced, the person reproducing it attempted it with an AMD GPU which is already supported via ROCm even though this error seems to pertain to Intel GPUs specifically which are only supported via Vulkan (or openVINO if you modified the source to support it and use VINO models). While I'm glad that Intel is attempting to be supported via Vulkan, I believe that the support is buggier than if it has been incorporated in via OneAPI instead. I guess you are right. I receive the same error when trying to call `/api/embed` on the `bge-m3:latest` model in Ollama 0.14.0 with Vulkan support enabled. I'm using an embedded Intel Iris XE GPU. Here is my error log: [ollama-0.14.0_bge-m3_embed.error.txt](https://github.com/user-attachments/files/24625698/ollama-0.14.0_bge-m3_embed.error.txt)
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#8943