[GH-ISSUE #9803] ollama.exe run deepseek-r1:1.5b error #6412

New Issue

GiteaMirror · 2026-04-12T17:57:48-05:00

GiteaMirror commented

2026-04-12 17:57:48 -05:00

Originally created by @liangkx19 on GitHub (Mar 17, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9803

What is the issue?

1、set OLLAMA_DEBUG=true && ollama.exe serve
2、ollama.exe run run deepseek-r1:1.5b => error

Relevant log output

2025/03/17 11:17:26 routes.go:1187: INFO server config env="map[CUDA_VISIBLE_DEVICES:-1 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:true OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\\Ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-03-17T11:17:26.301+08:00 level=INFO source=images.go:432 msg="total blobs: 9"
time=2025-03-17T11:17:26.316+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-03-17T11:17:26.321+08:00 level=INFO source=routes.go:1238 msg="Listening on 127.0.0.1:11434 (version 0.5.7)"
time=2025-03-17T11:17:26.321+08:00 level=DEBUG source=common.go:80 msg="runners located" dir="D:\\Ollama\\lib\\ollama\\runners"
time=2025-03-17T11:17:26.326+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu\\ollama_llama_server.exe"
time=2025-03-17T11:17:26.327+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx\\ollama_llama_server.exe"
time=2025-03-17T11:17:26.327+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx2\\ollama_llama_server.exe"
time=2025-03-17T11:17:26.328+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11\\ollama_llama_server.exe"
time=2025-03-17T11:17:26.328+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11_avx\\ollama_llama_server.exe"
time=2025-03-17T11:17:26.329+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v12\\ollama_llama_server.exe"
time=2025-03-17T11:17:26.329+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v12_avx\\ollama_llama_server.exe"
time=2025-03-17T11:17:26.330+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_avx\\ollama_llama_server.exe"
time=2025-03-17T11:17:26.330+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_v6.1\\ollama_llama_server.exe"
time=2025-03-17T11:17:26.331+08:00 level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu_avx2 cuda_v11 cuda_v12 cpu cpu_avx cuda_v11_avx cuda_v12_avx rocm_avx rocm_v6.1]"
time=2025-03-17T11:17:26.332+08:00 level=DEBUG source=routes.go:1268 msg="Override detection logic by setting OLLAMA_LLM_LIBRARY"
time=2025-03-17T11:17:26.332+08:00 level=DEBUG source=sched.go:105 msg="starting llm scheduler"
time=2025-03-17T11:17:26.333+08:00 level=INFO source=gpu.go:226 msg="looking for compatible GPUs"
time=2025-03-17T11:17:26.333+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-03-17T11:17:26.333+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=6 efficiency=0 threads=12
time=2025-03-17T11:17:26.334+08:00 level=DEBUG source=gpu.go:99 msg="searching for GPU discovery libraries for NVIDIA"
time=2025-03-17T11:17:26.336+08:00 level=DEBUG source=gpu.go:517 msg="Searching for GPU library" name=nvml.dll
time=2025-03-17T11:17:26.337+08:00 level=DEBUG source=gpu.go:543 msg="gpu library search" globs="[D:\\Ollama\\lib\\ollama\\nvml.dll D:\\Ollama\\lib\\ollama\\nvml.dll C:\\Program Files\\Python39\\Scripts\\nvml.dll C:\\Program Files\\Python39\\nvml.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\nvml.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\nvml.dll C:\\Oracle\\product\\11.2.0\\client_2\\bin\\nvml.dll C:\\Oracle\\product\\11.2.0\\client_1\\nvml.dll C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath\\nvml.dll C:\\windows\\system32\\nvml.dll C:\\windows\\nvml.dll C:\\windows\\System32\\Wbem\\nvml.dll C:\\windows\\System32\\WindowsPowerShell\\v1.0\\nvml.dll C:\\windows\\System32\\OpenSSH\\nvml.dll C:\\Program Files (x86)\\Enterprise Vault\\EVClient\\x64\\nvml.dll C:\\Program Files (x86)\\Java\\jre6\\bin\\nvml.dll C:\\Program Files\\Microsoft VS Code\\bin\\nvml.dll C:\\Program Files\\TortoiseSVN\\bin\\nvml.dll C:\\Program Files\\nodejs\\nvml.dll C:\\Program Files\\Citrix\\System32\\nvml.dll C:\\Program Files\\Citrix\\ICAService\\nvml.dll C:\\Program Files\\Git\\cmd\\nvml.dll C:\\Users\\Test\\AppData\\Local\\Microsoft\\WindowsApps\\nvml.dll C:\\Users\\localadmin\\AppData\\Roaming\\npm\\nvml.dll C:\\Users\\Test\\AppData\\Local\\ms-playwright\\chromium-1091\\chromium-win64\\chrome-win\\chrome.exe\\nvml.dll C:\\Users\\Test\\AppData\\Roaming\\Python\\Python39\\Scripts\\nvml.dll D:\\Ollama\\nvml.dll c:\\Windows\\System32\\nvml.dll]"
time=2025-03-17T11:17:26.344+08:00 level=DEBUG source=gpu.go:576 msg="discovered GPU libraries" paths=[]
time=2025-03-17T11:17:26.337+08:00 level=DEBUG source=gpu.go:543 msg="gpu library search" globs="[D:\\Ollama\\lib\\ollama\\nvml.dll D:\\Ollama\\lib\\ollama\\nvml.dll C:\\Program Files\\Python39\\Scripts\\nvml.dll C:\\Program Files\\Python39\\nvml.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\nvml.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\nvml.dll C:\\Oracle\\product\\11.2.0\\client_2\\bin\\nvml.dll C:\\Oracle\\product\\11.2.0\\client_1\\nvml.dll C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath\\nvml.dll C:\\windows\\system32\\nvml.dll C:\\windows\\nvml.dll C:\\windows\\System32\\Wbem\\nvml.dll C:\\windows\\System32\\WindowsPowerShell\\v1.0\\nvml.dll C:\\windows\\System32\\OpenSSH\\nvml.dll C:\\Program Files (x86)\\Enterprise Vault\\EVClient\\x64\\nvml.dll C:\\Program Files (x86)\\Java\\jre6\\bin\\nvml.dll C:\\Program Files\\Microsoft VS Code\\bin\\nvml.dll C:\\Program Files\\TortoiseSVN\\bin\\nvml.dll C:\\Program Files\\nodejs\\nvml.dll C:\\Program Files\\Citrix\\System32\\nvml.dll C:\\Program Files\\Citrix\\ICAService\\nvml.dll C:\\Program Files\\Git\\cmd\\nvml.dll C:\\Users\\Test\\AppData\\Local\\Microsoft\\WindowsApps\\nvml.dll C:\\Users\\localadmin\\AppData\\Roaming\\npm\\nvml.dll C:\\Users\\Test\\AppData\\Local\\ms-playwright\\chromium-1091\\chromium-win64\\chrome-win\\chrome.exe\\nvml.dll C:\\Users\\Test\\AppData\\Roaming\\Python\\Python39\\Scripts\\nvml.dll D:\\Ollama\\nvml.dll c:\\Windows\\System32\\nvml.dll]"
time=2025-03-17T11:17:26.344+08:00 level=DEBUG source=gpu.go:576 msg="discovered GPU libraries" paths=[]
time=2025-03-17T11:17:26.345+08:00 level=DEBUG source=gpu.go:517 msg="Searching for GPU library" name=nvcuda.dll
time=2025-03-17T11:17:26.346+08:00 level=DEBUG source=gpu.go:543 msg="gpu library search" globs="[D:\\Ollama\\lib\\ollama\\nvcuda.dll D:\\Ollama\\lib\\ollama\\nvcuda.dll C:\\Program Files\\Python39\\Scripts\\nvcuda.dll C:\\Program Files\\Python39\\nvcuda.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\nvcuda.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\nvcuda.dll C:\\Oracle\\product\\11.2.0\\client_2\\bin\\nvcuda.dll C:\\Oracle\\product\\11.2.0\\client_1\\nvcuda.dll C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath\\nvcuda.dll C:\\windows\\system32\\nvcuda.dll C:\\windows\\nvcuda.dll C:\\windows\\System32\\Wbem\\nvcuda.dll C:\\windows\\System32\\WindowsPowerShell\\v1.0\\nvcuda.dll C:\\windows\\System32\\OpenSSH\\nvcuda.dll C:\\Program Files (x86)\\Enterprise Vault\\EVClient\\x64\\nvcuda.dll C:\\Program Files (x86)\\Java\\jre6\\bin\\nvcuda.dll C:\\Program Files\\Microsoft VS Code\\bin\\nvcuda.dll C:\\Program Files\\TortoiseSVN\\bin\\nvcuda.dll C:\\Program Files\\nodejs\\nvcuda.dll C:\\Program Files\\Citrix\\System32\\nvcuda.dll C:\\Program Files\\Citrix\\ICAService\\nvcuda.dll C:\\Program Files\\Git\\cmd\\nvcuda.dll C:\\Users\\Test\\AppData\\Local\\Microsoft\\WindowsApps\\nvcuda.dll C:\\Users\\localadmin\\AppData\\Roaming\\npm\\nvcuda.dll C:\\Users\\Test\\AppData\\Local\\ms-playwright\\chromium-1091\\chromium-win64\\chrome-win\\chrome.exe\\nvcuda.dll C:\\Users\\Test\\AppData\\Roaming\\Python\\Python39\\Scripts\\nvcuda.dll D:\\Ollama\\nvcuda.dll c:\\windows\\system*\\nvcuda.dll]"
time=2025-03-17T11:17:26.357+08:00 level=DEBUG source=gpu.go:576 msg="discovered GPU libraries" paths=[C:\windows\system32\nvcuda.dll]

initializing C:\windows\system32\nvcuda.dll
dlsym: cuInit - 00007FFED4855010
dlsym: cuDriverGetVersion - 00007FFED485AB91
dlsym: cuDeviceGetCount - 00007FFED4856C21
dlsym: cuDeviceGet - 00007FFED4855A15
dlsym: cuDeviceGetAttribute - 00007FFED485970A
dlerr: 找不到指定的程序。

time=2025-03-17T11:17:26.384+08:00 level=INFO source=gpu.go:630 msg="Unable to load cudart library C:\\windows\\system32\\nvcuda.dll: symbol lookup for cuDeviceGetUuid failed: \xd5?\xbb\xb5\xbd?\xb6\xa8\xb5?\xcc\xd0\xf2\xa1\xa3\r\n"
time=2025-03-17T11:17:26.385+08:00 level=DEBUG source=gpu.go:517 msg="Searching for GPU library" name=cudart64_*.dll
time=2025-03-17T11:17:26.386+08:00 level=DEBUG source=gpu.go:543 msg="gpu library search" globs="[D:\\Ollama\\lib\\ollama\\cudart64_*.dll D:\\Ollama\\lib\\ollama\\cudart64_*.dll C:\\Program Files\\Python39\\Scripts\\cudart64_*.dll C:\\Program Files\\Python39\\cudart64_*.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\cudart64_*.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\cudart64_*.dll C:\\Oracle\\product\\11.2.0\\client_2\\bin\\cudart64_*.dll C:\\Oracle\\product\\11.2.0\\client_1\\cudart64_*.dll C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath\\cudart64_*.dll C:\\windows\\system32\\cudart64_*.dll C:\\windows\\cudart64_*.dll C:\\windows\\System32\\Wbem\\cudart64_*.dll C:\\windows\\System32\\WindowsPowerShell\\v1.0\\cudart64_*.dll C:\\windows\\System32\\OpenSSH\\cudart64_*.dll C:\\Program Files (x86)\\Enterprise Vault\\EVClient\\x64\\cudart64_*.dll C:\\Program Files (x86)\\Java\\jre6\\bin\\cudart64_*.dll C:\\Program Files\\Microsoft VS Code\\bin\\cudart64_*.dll C:\\Program Files\\TortoiseSVN\\bin\\cudart64_*.dll C:\\Program Files\\nodejs\\cudart64_*.dll C:\\Program Files\\Citrix\\System32\\cudart64_*.dll C:\\Program Files\\Git\\cmd\\cudart64_*.dll C:\\Users\\Test\\AppData\\Local\\Microsoft\\WindowsApps\\cudart64_*.dll C:\\Users\\localadmin\\AppData\\Roaming\\npm\\cudart64_*.dll C:\\Users\\Test\\AppData\\Local\\ms-playwright\\chromium-1091\\chromium-win64\\chrome-win\\chrome.exe\\cudart64_*.dllC:\\Users\\Test\\AppData\\Roaming\\Python\\Python39\\Scripts\\cudart64_*.dll D:\\Ollama\\cudart64_*.dll C:\\Users\\Test\\AppData\\Local\\Programs\\Ollama\\cudart64_*.dll D:\\Ollama\\lib\\ollama\\cudart64_*.dll D:\\Ollama\\lib\\ollama\\cudart64_*.dll c:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v*\\bin\\cudart64_*.dll]"
time=2025-03-17T11:17:26.444+08:00 level=DEBUG source=gpu.go:576 msg="discovered GPU libraries" paths="[D:\\Ollama\\lib\\ollama\\cudart64_110.dll D:\\Ollama\\lib\\ollama\\cudart64_12.dll]"
cudaSetDevice err: 100
time=2025-03-17T11:17:26.878+08:00 level=DEBUG source=gpu.go:592 msg="Unable to load cudart library D:\\Ollama\\lib\\ollama\\cudart64_110.dll: cudart init failure: 100"
cudaSetDevice err: 35
time=2025-03-17T11:17:26.883+08:00 level=DEBUG source=gpu.go:592 msg="Unable to load cudart library D:\\Ollama\\lib\\ollama\\cudart64_12.dll: your nvidia driver is too old or missing.  If you have a CUDA GPU please upgrade to run ollama"
time=2025-03-17T11:17:26.886+08:00 level=DEBUG source=amd_windows.go:35 msg="unable to load amdhip64_6.dll, please make sure to upgrade to the latest amd driver: The specified module could not be found."
time=2025-03-17T11:17:26.886+08:00 level=INFO source=gpu.go:392 msg="no compatible GPUs were discovered"
time=2025-03-17T11:17:26.887+08:00 level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="15.9 GiB" available="8.3 GiB"


time=2025-03-17T11:55:42.710+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.711+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.711+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx2\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.712+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.712+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11_avx\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.713+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v12\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.714+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_avx\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.715+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_v6.1\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.716+08:00 level=DEBUG source=memory.go:107 msg=evaluating library=cpu gpu_count=1 available="[8.3 GiB]"
time=2025-03-17T11:55:42.718+08:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=29 layers.offload=0 layers.split="" memory.available="[8.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.5 GiB" memory.required.partial="0 B" memory.required.kv="224.0 MiB" memory.required.allocations="[1.5 GiB]" memory.weights.total="976.1 MiB" memory.weights.repeating="793.5 MiB" memory.weights.nonrepeating="182.6 MiB" memory.graph.full="299.8 MiB" memory.graph.partial="482.3 MiB"
time=2025-03-17T11:55:42.722+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.722+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.723+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx2\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.723+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.724+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11_avx\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.729+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v12\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.729+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v12_avx\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.730+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_avx\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.730+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_v6.1\\ollama_llama_server.exe"
time=2025-03-17T11:55:42.747+08:00 level=DEBUG source=gpu.go:713 msg="no filter required for library cpu"
time=2025-03-17T11:55:42.747+08:00 level=INFO source=server.go:376 msg="starting llama server" cmd="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx2\\ollama_llama_server.exe runner --model D:\\Ollama\\models\\blobs\\sha256-aabd4debf0c8f08881923f2c25fc0fdeed24435271c2b3e92c4af36704040dbc --ctx-size 8192 --batch-size 512 --verbose --threads 6 --no-mmap --parallel 4 --port 8510"
time=2025-03-17T11:55:42.748+08:00 level=DEBUG source=server.go:393 msg=subprocess environment="[PATH=D:\\Ollama\\lib\\ollama;D:\\Ollama\\lib\\ollama;D:\\Ollama\\lib\\ollama\\runners\\cpu_avx2;C:\\Program Files\\Python39\\Scripts\\;C:\\Program Files\\Python39\\;C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\;C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\;C:\\Oracle\\product\\11.2.0\\client_2\\bin;C:\\Oracle\\product\\11.2.0\\client_1;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\windows\\system32;C:\\windows;C:\\windows\\System32\\Wbem;C:\\windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\windows\\System32\\OpenSSH\\;C:\\Program Files (x86)\\Enterprise Vault\\EVClient\\x64\\;C:\\Program Files (x86)\\Java\\jre6\\bin;C:\\Program Files\\Microsoft VS Code\\bin;C:\\Program Files\\TortoiseSVN\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\Citrix\\System32\\;C:\\Program Files\\Citrix\\ICAService\\;C:\\Program Files\\Git\\cmd;C:\\Users\\Test\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\localadmin\\AppData\\Roaming\\npm;C:\\Users\\Test\\AppData\\Local\\ms-playwright\\chromium-1091\\chromium-win64\\chrome-win\\chrome.exe;C:\\Users\\Test\\AppData\\Roaming\\Python\\Python39\\Scripts;]"
time=2025-03-17T11:55:42.773+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-03-17T11:55:42.773+08:00 level=INFO source=server.go:555 msg="waiting for llama runner to start responding"
Exception 0xc0000006 0x0 0x700000000 0x7fff40a1105e
PC=0x7fff40a1105e
signal arrived during external code execution

runtime.cgocall(0x7ff78e6ba0e0, 0xc000438b30)
        runtime/cgocall.go:167 +0x3e fp=0xc0005c6d08 sp=0xc0005c6ca0 pc=0x7ff78e6a9c3e
runtime.syscall_syscalln(0xc0005c6da8?, 0x5d0?, {0xc0005c6d50?, 0x0?, 0xc000438808?})
        runtime/syscall_windows.go:521 +0x4e fp=0xc0005c6d28 sp=0xc0005c6d08 pc=0x7ff78e698f2e
syscall.Syscall9(0x6?, 0xc0005c6e08?, 0x7ff78e6ddc48?, 0x7ff7900e4660?, 0xc000161c00?, 0x200000003?, 0x0?, 0x0?, 0xc000161c00?, 0x0, ...)
        runtime/syscall_windows.go:469 +0x57 fp=0xc0005c6da8 sp=0xc0005c6d28 pc=0x7ff78e6b4597
syscall.WSAIoctl(0x5d0, 0xc8000006, 0x7ff78e6ba0e0?, 0x10, 0x0?, 0x8, 0x7fff4b905b30?, 0x9?, 0x0)
        syscall/zsyscall_windows.go:1277 +0xd2 fp=0xc0005c6e38 sp=0xc0005c6da8 pc=0x7ff78e6dca72
syscall.LoadConnectEx.func1()
        syscall/syscall_windows.go:1051 +0xbf fp=0xc0005c6eb0 sp=0xc0005c6e38 pc=0x7ff78e6ddd9f
sync.(*Once).doSlow(0x4?, 0x0?)
        sync/once.go:76 +0xb4 fp=0xc0005c6f10 sp=0xc0005c6eb0 pc=0x7ff78e6c8294
sync.(*Once).Do(...)
        sync/once.go:67
syscall.LoadConnectEx()
syscall/syscall_windows.go:1043 +0x2c fp=0xc0005c6f30 sp=0xc0005c6f10 pc=0x7ff78e6d616c
syscall.ConnectEx(0x5b4, {0x7ff78f893060, 0xc00022c020}, 0x0, 0x0, 0x0, 0xc000524368)
        syscall/syscall_windows.go:1075 +0x3f fp=0xc0005c6f88 sp=0xc0005c6f30 pc=0x7ff78e6d62df
internal/poll.(*FD).ConnectEx.func1(0xc0005c7058?)
        internal/poll/fd_windows.go:937 +0x3e fp=0xc0005c6fd0 sp=0xc0005c6f88 pc=0x7ff78e74ef9e
internal/poll.execIO(0xc000524368, 0x7ff78f75d238)
        internal/poll/fd_windows.go:161 +0x7b fp=0xc0005c7048 sp=0xc0005c6fd0 pc=0x7ff78e7462bb
internal/poll.(*FD).ConnectEx(0x5b4?, {0x7ff78f893060?, 0xc00022c020?})
        internal/poll/fd_windows.go:936 +0x54 fp=0xc0005c7068 sp=0xc0005c7048 pc=0x7ff78e74a8d4
net.(*netFD).connect(0xc000524288, {0x7ff78f89baf0, 0xc0005aeaf0}, {0x0, 0x0?}, {0x7ff78f893060, 0xc00022c020})
        net/fd_windows.go:149 +0x4dd fp=0xc0005c71a8 sp=0xc0005c7068 pc=0x7ff78e7b1bdd
net.(*netFD).dial(0xc000524288, {0x7ff78f89baf0, 0xc0005aeaf0}, {0x7ff78f89f2a0?, 0x0?}, {0x7ff78f89f2a0, 0xc000782de0}, 0x7ff78e7b558b?)
        net/sock_posix.go:124 +0x3c5 fp=0xc0005c7280 sp=0xc0005c71a8 pc=0x7ff78e7c4585
net.socket({0x7ff78f89baf0, 0xc0005aeaf0}, {0x7ff78f6d96b8, 0x3}, 0x2, 0x1, 0x20?, 0x0, {0x7ff78f89f2a0, 0x0}, ...)
        net/sock_posix.go:70 +0x2af fp=0xc0005c7328 sp=0xc0005c7280usage: D:\Ollama\lib\ollama\runners\cpu_avx2\ollama_llama_server.exe [options]
e pc=
rror: unknown argument: runner
0x7ff78e7c40cfoptions:
-h, --help                show this help message and exit
net.internetSocket  -v, --verbose             verbose output (default: disabled)
(  -t N, --threads N         number of threads to use during computation (default: -1)
{  -tb N, --threads-batch N  number of threads to use during batch and prompt processing (default: same as --threads)
0x7ff78f89baf0  --threads-http N          number of threads in the http server pool to process requests (default: max(hardware concurrency - 1, --parallel N + 2))
,   -c N, --ctx-size N        size of the prompt context (default: 0)
0xc0005aeaf0  --rope-scaling {none,linear,yarn}
}                            RoPE frequency scaling method, defaults to linear unless specified by the model
,   --rope-freq-base N        RoPE base frequency (default: loaded from model)
{  --rope-freq-scale N       RoPE frequency scaling factor, expands context by a factor of 1/N
  --yarn-ext-factor N       YaRN: extrapolation mix factor (default: 1.0, 0.0 = full interpolation)
  --yarn-attn-factor N      YaRN: scale sqrt(t) or attention magnitude (default: 1.0)
0x7ff78f6d96b8  --yarn-beta-slow N        YaRN: high correction dim or alpha (default: 1.0)
,   --yarn-beta-fast N        YaRN: low correction dim or beta (default: 32.0)
0x3  --pooling {none,mean,cls}
                        pooling type for embeddings, use model default if unspecified
}  -b N, --batch-size N      batch size for prompt processing (default: 2048)
for memory key+value (default: disabled)
{                            not recommended: doubles context memory required and no measurable increase in quality
0x7ff78f89f2a0  --mlock                   force system to keep model in RAM rather than swapping or compressing
,   --no-mmap                 do not memory-map model (slower load but may reduce pageouts if not using mlock)
  --numa TYPE               attempt optimizations that help on some NUMA systems
0x0                              - distribute: spread execution evenly over all nodes
}                              - isolate: only spawn threads on CPUs on the node that execution started on
,                               - numactl: use the CPU map provided my numactl
{  -m FNAME, --model FNAME
0x7ff78f89f2a0                            model path (default: )
  -a ALIAS, --alias ALIAS
?                            set an alias for the model, will be added as `model` field in completion response
,   --lora FNAME              apply LoRA adapter (implies --no-mmap)
0xc000782de0  --lora-base FNAME         optional model to use as a base for the layers modified by the LoRA adapter
?}  --host                    ip address to listen (default  (default: 127.0.0.1)
,   --port PORT               port to listen (default  (default: 8080)
0x1  --path PUBLIC_PATH        path from which to serve static files (default examples/server/public)
,   --api-key API_KEY         optional api key to enhance server security. If set, requests must include this key for access.
0x0  --api-key-file FNAME      path to file containing api keys delimited by new lines. If set, requests must include one of the keys for access.
, ...)
-to N, --timeout N        server read/write timeout in seconds (default: 600)
net/ipsock_posix.go  --embedding               enable embedding vector output (default: disabled)
:  -np N, --parallel N       number of slots for process requests (default: 1)
167 +  -cb, --cont-batching      enable continuous batching (a.k.a dynamic batching) (default: disabled)
0x1e5  -fa, --flash-attn         enable Flash Attention (default: disabled)
 fp=  -spf FNAME, --system-prompt-file FNAME
0xc0005c73b0 sp=                            set a file to load a system prompt (initial prompt of all slots), this is useful for chat applications.
0xc0005c7328  -ctk TYPE, --cache-type-k TYPE
 pc=                            KV cache data type for K (default: f16)
0x7ff78e7bb425  -ctv TYPE, --cache-type-v TYPE
KV cache data type for V (default: f16)
net.(*sysDialer).doDialTCPProto  --mmproj MMPROJ_FILE      path to a multimodal projector file for LLaVA.
(  --log-format              log output format: json or text (default: json)
0xc000000480  --log-disable             disables logging to a file.
, {0x7ff78f89baf0, 0xc0005aeaf0  --slots-endpoint-disable  disables slots monitoring endpoint.
}  --metrics                 enable prometheus compatible metrics endpoint (default: disabled).
,
0x0  -n, --n-predict           maximum tokens to predict (default: -1)
,   --override-kv KEY=TYPE:VALUE
0xc000782de0                            advanced option to override model metadata by key. may be specified multiple times.
,                             types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false
0x0)
-gan N, --grp-attn-n N    set the group attention factor to extend context size through self-extend(default: 1=disabled), used together with group attention width `--grp-attn-w`
        net/tcpsock_posix.go  -gaw N, --grp-attn-w N    set the group attention width to extend context size through self-extend(default: 512), used together with group attention factor `--grp-attn-n`
:  --chat-template JINJA_TEMPLATE
85                            set custom jinja chat template (default: template taken from model's metadata)
 +                            Note: only commonly used templates are accepted, since we don't have jinja parser
0xec
 fp=0xc0005c7460 sp=0xc0005c73b0 pc=0x7ff78e7c806c
net.(*sysDialer).doDialTCP(...)
        net/tcpsock_posix.go:75
net.(*sysDialer).dialTCP(0xc0006834c8?, {0x7ff78f89baf0?, 0xc0005aeaf0?}, 0x7ff78f5a0400?, 0xc000683538?)
net/tcpsock_posix.go:71 +0x69 fp=0xc0005c74a0 sp=0xc0005c7460 pc=0x7ff78e7c7f09
net.(*sysDialer).dialSingle(0xc000000480, {0x7ff78f89baf0, 0xc0005aeaf0}, {0x7ff78f8962b8, 0xc000782de0})
        net/dial.go:670 +0x27d fp=0xc0005c7570 sp=0xc0005c74a0 pc=0x7ff78e7a975d
net.(*sysDialer).dialSerial(0xc000000480, {0x7ff78f89baf0, 0xc0005aeaf0}, {0xc00017cb60?, 0x1, 0xc000782db0?})
        net/dial.go:635 +0x24e fp=0xc0005c7678 sp=0xc0005c7570 pc=0x7ff78e7a908e
net.(*sysDialer).dialParallel(0xc00017cb40?, {0x7ff78f89baf0?, 0xc0005aeaf0?}, {0xc00017cb60?, 0xc0005aeaf0?, 0x7ff78f6da33f?}, {0x0?, 0x7ff78f6d96b8?, 0x10?})
        net/dial.go:536 +0x3a7 fp=0xc0005c7890 sp=0xc0005c7678 pc=0x7ff78e7a8767
net.(*Dialer).DialContext(0xc0000f9320, {0x7ff78f89ba80, 0xc000882320}, {0x7ff78f6d96b8, 0x3}, {0xc0007809e0, 0xe})
        net/dial.go:527 +0x6a5 fp=0xc0005c79b0 sp=0xc0005c7890 pc=0x7ff78e7a81e5
net.(*Dialer).DialContext-fm({0x7ff78f89ba80?, 0xc000882320?}, {0x7ff78f6d96b8?, 0x7ff790155020?}, {0xc0007809e0?, 0xc000683a50?})
        <autogenerated>:1 +0x49 fp=0xc0005c79f8 sp=0xc0005c79b0 pc=0x7ff78ea13f49
net/http.(*Transport).dial(0x0?, {0x7ff78f89ba80?, 0xc000882320?}, {0x7ff78f6d96b8?, 0x0?}, {0xc0007809e0?, 0x0?})
net/http/transport.go:1226 +0xd2 fp=0xc0005c7a60 sp=0xc0005c79f8 pc=0x7ff78e9fa112
net/http.(*Transport).dialConn(0x7ff7900f8b20, {0x7ff78f89ba80, 0xc000882320}, {{}, 0x0, {0xc00037c8e0, 0x4}, {0xc0007809e0, 0xe}, 0x0})
        net/http/transport.go:1728 +0x7e5 fp=0xc0005c7ed8 sp=0xc0005c7a60 pc=0x7ff78e9fd265
net/http.(*Transport).dialConnFor(0x7ff7900f8b20, 0xc000151a20)
        net/http/transport.go:1563 +0xb8 fp=0xc0005c7f88 sp=0xc0005c7ed8 pc=0x7ff78e9fbd58
net/http.(*Transport).startDialConnForLocked.func1()
        net/http/transport.go:1545 +0x35 fp=0xc0005c7fe0 sp=0xc0005c7f88 pc=0x7ff78e9fbb95
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0005c7fe8 sp=0xc0005c7fe0 pc=0x7ff78e6b8921
created by net/http.(*Transport).startDialConnForLocked in goroutine 11
        net/http/transport.go:1544 +0x117
goroutine 1 gp=0xc000068000 m=nil [IO wait]:
runtime.gopark(0x7ff78e6ba0e0?, 0x7ff7900e3e20?, 0x20?, 0x40?, 0xc0005240cc?)
        runtime/proc.go:424 +0xce fp=0xc0006875f0 sp=0xc0006875d0 pc=0x7ff78e6b03ee
runtime.netpollblock(0x268?, 0x8e648386?, 0xf7?)
        runtime/netpoll.go:575 +0xf7 fp=0xc000687628 sp=0xc0006875f0 pc=0x7ff78e674fb7
internal/poll.runtime_pollWait(0x2ba670fdb10, 0x72)
        runtime/netpoll.go:351 +0x85 fp=0xc000687648 sp=0xc000687628 pc=0x7ff78e6af665
internal/poll.(*pollDesc).wait(0x7ff78e7438d5?, 0x7ff78e6aae9d?, 0x0)
        internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000687670 sp=0xc000687648 pc=0x7ff78e744f07
internal/poll.execIO(0xc000524020, 0xc0003ad718)
        internal/poll/fd_windows.go:177 +0x105 fp=0xc0006876e8 sp=0xc000687670 pc=0x7ff78e746345
internal/poll.(*FD).acceptOne(0xc000524008, 0x40c, {0xc0001705a0?, 0xc0003ad778?, 0x7ff78e74e0c5?}, 0xc0003ad7ac?)
internal/poll/fd_windows.go:946 +0x65 fp=0xc000687748 sp=0xc0006876e8 pc=0x7ff78e74a985
internal/poll.(*FD).Accept(0xc000524008, 0xc0006878f8)
        internal/poll/fd_windows.go:980 +0x1b6 fp=0xc000687800 sp=0xc000687748 pc=0x7ff78e74acb6
net.(*netFD).accept(0xc000524008)
        net/fd_windows.go:182 +0x4b fp=0xc000687918 sp=0xc000687800 pc=0x7ff78e7b23cb
net.(*TCPListener).accept(0xc000248080)
        net/tcpsock_posix.go:159 +0x1e fp=0xc000687968 sp=0xc000687918 pc=0x7ff78e7c853e
net.(*TCPListener).Accept(0xc000248080)
        net/tcpsock.go:372 +0x30 fp=0xc000687998 sp=0xc000687968 pc=0x7ff78e7c72f0
net/http.(*onceCloseListener).Accept(0xc0000f9cb0?)
        <autogenerated>:1 +0x24 fp=0xc0006879b0 sp=0xc000687998 pc=0x7ff78ea12e44
net/http.(*Server).Serve(0xc0006002d0, {0x7ff78f899760, 0xc000248080})
        net/http/server.go:3330 +0x30c fp=0xc000687ae0 sp=0xc0006879b0 pc=0x7ff78e9eadcc
github.com/ollama/ollama/server.Serve({0x7ff78f899760, 0xc000248080})
        github.com/ollama/ollama/server/routes.go:1277 +0x8cc fp=0xc000687d18 sp=0xc000687ae0 pc=0x7ff78f22e96c
github.com/ollama/ollama/cmd.RunServer(0xc000124900?, {0x7ff790155020?, 0x4?, 0x7ff78f6da1ef?})
github.com/ollama/ollama/cmd/cmd.go:1033 +0x4a fp=0xc000687d58 sp=0xc000687d18 pc=0x7ff78f25daaa
github.com/spf13/cobra.(*Command).execute(0xc0001de608, {0x7ff790155020, 0x0, 0x0})
        github.com/spf13/cobra@v1.7.0/command.go:940 +0x862 fp=0xc000687e78 sp=0xc000687d58 pc=0x7ff78e82c122
github.com/spf13/cobra.(*Command).ExecuteC(0xc0001e9508)
        github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000687f30 sp=0xc000687e78 pc=0x7ff78e82c965
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=0xc000687f50 sp=0xc000687f30 pc=0x7ff78f265c8d
runtime.main()
        runtime/proc.go:272 +0x27d fp=0xc000687fe0 sp=0xc000687f50 pc=0x7ff78e67dfbd
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000687fe8 sp=0xc000687fe0 pc=0x7ff78e6b8921
goroutine 2 gp=0xc000068700 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00006bfa8 sp=0xc00006bf88 pc=0x7ff78e6b03ee
runtime.goparkunlock(...)
        runtime/proc.go:430
runtime.forcegchelper()
        runtime/proc.go:337 +0xb8 fp=0xc00006bfe0 sp=0xc00006bfa8 pc=0x7ff78e67e2d8
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00006bfe8 sp=0xc00006bfe0 pc=0x7ff78e6b8921
created by runtime.init.7 in goroutine 1
        runtime/proc.go:325 +0x1a

goroutine 3 gp=0xc000068a80 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00006df80 sp=0xc00006df60 pc=0x7ff78e6b03ee
runtime.goparkunlock(...)
        runtime/proc.go:430
runtime.bgsweep(0xc00007a000)
        runtime/mgcsweep.go:317 +0xdf fp=0xc00006dfc8 sp=0xc00006df80 pc=0x7ff78e666fbf
runtime.gcenable.gowrap1()
        runtime/mgc.go:204 +0x25 fp=0xc00006dfe0 sp=0xc00006dfc8 pc=0x7ff78e65b5e5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00006dfe8 sp=0xc00006dfe0 pc=0x7ff78e6b8921
created by runtime.gcenable in goroutine 1
        runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000068c40 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x7ff78f888818?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000085f78 sp=0xc000085f58 pc=0x7ff78e6b03ee
runtime.goparkunlock(...)
        runtime/proc.go:430
runtime.(*scavengerState).park(0x7ff790108560)
        runtime/mgcscavenge.go:425 +0x49 fp=0xc000085fa8 sp=0xc000085f78 pc=0x7ff78e664989
runtime.bgscavenge(0xc00007a000)
        runtime/mgcscavenge.go:658 +0x59 fp=0xc000085fc8 sp=0xc000085fa8 pc=0x7ff78e664f19
runtime.gcenable.gowrap2()
        runtime/mgc.go:205 +0x25 fp=0xc000085fe0 sp=0xc000085fc8 pc=0x7ff78e65b585
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff78e6b8921
created by runtime.gcenable in goroutine 1
        runtime/mgc.go:205 +0xa5

goroutine 5 gp=0xc000069180 m=nil [finalizer wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000087e20 sp=0xc000087e00 pc=0x7ff78e6b03ee
runtime.runfinq()
        runtime/mfinal.go:193 +0x107 fp=0xc000087fe0 sp=0xc000087e20 pc=0x7ff78e65a6a7
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000087fe8 sp=0xc000087fe0 pc=0x7ff78e6b8921
created by runtime.createfing in goroutine 1
        runtime/mfinal.go:163 +0x3d
goroutine 6 gp=0xc000160a80 m=nil [chan receive]:
runtime.gopark(0xc00006ff60?, 0x7ff78e79be85?, 0x10?, 0xe8?, 0x7ff78f8b0080?)
        runtime/proc.go:424 +0xce fp=0xc00006ff18 sp=0xc00006fef8 pc=0x7ff78e6b03ee
runtime.chanrecv(0xc00007e310, 0x0, 0x1)
        runtime/chan.go:639 +0x41e fp=0xc00006ff90 sp=0xc00006ff18 pc=0x7ff78e64acbe
time=2025-03-17T11:55:42.975+08:00 level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server not responding"
runtime.chanrecv1(0x7ff78e67e120?, 0xc00006ff76?)
        runtime/chan.go:489 +0x12 fp=0xc00006ffb8 sp=0xc00006ff90 pc=0x7ff78e64a872
runtime.unique_runtime_registerUniqueMapCleanup.func1(...)
        runtime/mgc.go:1781
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
        runtime/mgc.go:1784 +0x2f fp=0xc00006ffe0 sp=0xc00006ffb8 pc=0x7ff78e65e6cf
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00006ffe8 sp=0xc00006ffe0 pc=0x7ff78e6b8921
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
        runtime/mgc.go:1779 +0x96

goroutine 18 gp=0xc000208380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000081f38 sp=0xc000081f18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc000081fc8 sp=0xc000081f38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc000081fe0 sp=0xc000081fc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105
goroutine 19 gp=0xc000208540 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000083f38 sp=0xc000083f18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc000083fc8 sp=0xc000083f38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 20 gp=0xc000208700 m=nil [GC worker (idle)]:
runtime.gopark(0x9f6dea6b13c?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00041df38 sp=0xc00041df18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc00041dfc8 sp=0xc00041df38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00041dfe0 sp=0xc00041dfc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00041dfe8 sp=0xc00041dfe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105
goroutine 21 gp=0xc0002088c0 m=nil [GC worker (idle)]:
runtime.gopark(0x9f6dea6b13c?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00041ff38 sp=0xc00041ff18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc00041ffc8 sp=0xc00041ff38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00041ffe0 sp=0xc00041ffc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00041ffe8 sp=0xc00041ffe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 22 gp=0xc000208a80 m=nil [GC worker (idle)]:
runtime.gopark(0x9f6dea6b13c?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000419f38 sp=0xc000419f18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc000419fc8 sp=0xc000419f38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc000419fe0 sp=0xc000419fc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000419fe8 sp=0xc000419fe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105
goroutine 23 gp=0xc000208c40 m=nil [GC worker (idle)]:
runtime.gopark(0x9f6dea6b13c?, 0x3?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00041bf38 sp=0xc00041bf18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc00041bfc8 sp=0xc00041bf38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00041bfe0 sp=0xc00041bfc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00041bfe8 sp=0xc00041bfe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 24 gp=0xc000208e00 m=nil [GC worker (idle)]:
runtime.gopark(0x9f6dea6b13c?, 0x1?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000425f38 sp=0xc000425f18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc000425fc8 sp=0xc000425f38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc000425fe0 sp=0xc000425fc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000425fe8 sp=0xc000425fe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105
goroutine 25 gp=0xc000208fc0 m=nil [GC worker (idle)]:
runtime.gopark(0x9f6dea6b13c?, 0x3?, 0x70?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000427f38 sp=0xc000427f18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc000427fc8 sp=0xc000427f38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc000427fe0 sp=0xc000427fc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000427fe8 sp=0xc000427fe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105
goroutine 26 gp=0xc000209180 m=nil [GC worker (idle)]:
runtime.gopark(0x7ff790157040?, 0x1?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000421f38 sp=0xc000421f18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc000421fc8 sp=0xc000421f38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc000421fe0 sp=0xc000421fc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000421fe8 sp=0xc000421fe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 27 gp=0xc000209340 m=nil [GC worker (idle)]:
runtime.gopark(0x9f6dea6b13c?, 0x1?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000423f38 sp=0xc000423f18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc000423fc8 sp=0xc000423f38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc000423fe0 sp=0xc000423fc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000423fe8 sp=0xc000423fe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 28 gp=0xc000209500 m=nil [GC worker (idle)]:
runtime.gopark(0x9f6dea6b13c?, 0x1?, 0x8?, 0x9?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00042df38 sp=0xc00042df18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc00042dfc8 sp=0xc00042df38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00042dfe0 sp=0xc00042dfc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00042dfe8 sp=0xc00042dfe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105
goroutine 29 gp=0xc0002096c0 m=nil [GC worker (idle)]:
runtime.gopark(0x9f6dea6b13c?, 0x1?, 0x24?, 0xb1?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00042ff38 sp=0xc00042ff18 pc=0x7ff78e6b03ee
runtime.gcBgMarkWorker(0xc0002df1f0)
        runtime/mgc.go:1412 +0xe9 fp=0xc00042ffc8 sp=0xc00042ff38 pc=0x7ff78e65d9c9
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00042ffe0 sp=0xc00042ffc8 pc=0x7ff78e65d8a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00042ffe8 sp=0xc00042ffe0 pc=0x7ff78e6b8921
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 34 gp=0xc00043e540 m=0 mp=0x7ff79010b1e0 [syscall]:
runtime.notetsleepg(0x7ff790155ce0, 0xffffffffffffffff)
        runtime/lock_sema.go:296 +0x31 fp=0xc000429fa0 sp=0xc000429f68 pc=0x7ff78e650a51
os/signal.signal_recv()
        runtime/sigqueue.go:152 +0x29 fp=0xc000429fc0 sp=0xc000429fa0 pc=0x7ff78e6b1fe9
os/signal.loop()
        os/signal/signal_unix.go:23 +0x13 fp=0xc000429fe0 sp=0xc000429fc0 pc=0x7ff78ea15113
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000429fe8 sp=0xc000429fe0 pc=0x7ff78e6b8921
created by os/signal.Notify.func1.1 in goroutine 1
        os/signal/signal.go:151 +0x1f
goroutine 35 gp=0xc00043e700 m=nil [chan receive]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00042bf00 sp=0xc00042bee0 pc=0x7ff78e6b03ee
runtime.chanrecv(0xc0003f6d20, 0x0, 0x1)
        runtime/chan.go:639 +0x41e fp=0xc00042bf78 sp=0xc00042bf00 pc=0x7ff78e64acbe
runtime.chanrecv1(0x0?, 0x0?)
        runtime/chan.go:489 +0x12 fp=0xc00042bfa0 sp=0xc00042bf78 pc=0x7ff78e64a872
github.com/ollama/ollama/server.Serve.func2()
        github.com/ollama/ollama/server/routes.go:1255 +0x3d fp=0xc00042bfe0 sp=0xc00042bfa0 pc=0x7ff78f22ea3d
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00042bfe8 sp=0xc00042bfe0 pc=0x7ff78e6b8921
created by github.com/ollama/ollama/server.Serve in goroutine 1
        github.com/ollama/ollama/server/routes.go:1254 +0x667
goroutine 36 gp=0xc00043e8c0 m=nil [select]:
runtime.gopark(0xc0002bbf40?, 0x3?, 0x0?, 0x0?, 0xc0002bbcf2?)
        runtime/proc.go:424 +0xce fp=0xc0002bbb70 sp=0xc0002bbb50 pc=0x7ff78e6b03ee
runtime.selectgo(0xc0002bbf40, 0xc0002bbcec, 0xc000000240?, 0x0, 0x7ff78f707421?, 0x1)
        runtime/select.go:335 +0x7a5 fp=0xc0002bbc98 sp=0xc0002bbb70 pc=0x7ff78e68efe5
github.com/ollama/ollama/server.(*Scheduler).processPending(0xc000200180, {0x7ff78f89ba80, 0xc0000c8a50})
        github.com/ollama/ollama/server/sched.go:117 +0xcf fp=0xc0002bbfb8 sp=0xc0002bbc98 pc=0x7ff78f23274f
github.com/ollama/ollama/server.(*Scheduler).Run.func1()
        github.com/ollama/ollama/server/sched.go:107 +0x1f fp=0xc0002bbfe0 sp=0xc0002bbfb8 pc=0x7ff78f23265f
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0002bbfe8 sp=0xc0002bbfe0 pc=0x7ff78e6b8921
created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1
        github.com/ollama/ollama/server/sched.go:106 +0xb4
goroutine 37 gp=0xc00043ea80 m=nil [select]:
runtime.gopark(0xc0003a5f50?, 0x3?, 0x0?, 0x0?, 0xc0003a5d52?)
        runtime/proc.go:424 +0xce fp=0xc0003a5bd8 sp=0xc0003a5bb8 pc=0x7ff78e6b03ee
runtime.selectgo(0xc0003a5f50, 0xc0003a5d4c, 0x0?, 0x0, 0x0?, 0x1)
        runtime/select.go:335 +0x7a5 fp=0xc0003a5d00 sp=0xc0003a5bd8 pc=0x7ff78e68efe5
github.com/ollama/ollama/server.(*Scheduler).processCompleted(0xc000200180, {0x7ff78f89ba80, 0xc0000c8a50})
        github.com/ollama/ollama/server/sched.go:316 +0xec fp=0xc0003a5fb8 sp=0xc0003a5d00 pc=0x7ff78f2339cc
github.com/ollama/ollama/server.(*Scheduler).Run.func2()
        github.com/ollama/ollama/server/sched.go:111 +0x1f fp=0xc0003a5fe0 sp=0xc0003a5fb8 pc=0x7ff78f23261f
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0003a5fe8 sp=0xc0003a5fe0 pc=0x7ff78e6b8921
created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1
        github.com/ollama/ollama/server/sched.go:110 +0x110
goroutine 40 gp=0xc000160c40 m=nil [select]:
runtime.gopark(0xc0005c2f08?, 0x2?, 0x0?, 0x0?, 0xc0005c2eb4?)
        runtime/proc.go:424 +0xce fp=0xc0005c2cc8 sp=0xc0005c2ca8 pc=0x7ff78e6b03ee
runtime.selectgo(0xc0005c2f08, 0xc0005c2eb0, 0xffffffffffffffff?, 0x0, 0x0?, 0x1)
        runtime/select.go:335 +0x7a5 fp=0xc0005c2df0 sp=0xc0005c2cc8 pc=0x7ff78e68efe5
github.com/ollama/ollama/server.(*Server).scheduleRunner(0xc000008870, {0x7ff78f89ba80, 0xc000491bd0}, {0xc000630f60, 0x2b}, {0xc0004995f8, 0x1, 0x1}, 0x0, 0x0)
        github.com/ollama/ollama/server/routes.go:103 +0x5f7 fp=0xc0005c30f0 sp=0xc0005c2df0 pc=0x7ff78f21fff7
github.com/ollama/ollama/server.(*Server).GenerateHandler(0xc000008870, 0xc000125400)
        github.com/ollama/ollama/server/routes.go:176 +0x9a7 fp=0xc0005c36d8 sp=0xc0005c30f0 pc=0x7ff78f220a87
github.com/ollama/ollama/server.(*Server).GenerateHandler-fm(0x9?)
        <autogenerated>:1 +0x26 fp=0xc0005c36f8 sp=0xc0005c36d8 pc=0x7ff78f242e06
github.com/gin-gonic/gin.(*Context).Next(0xc000125400)
        github.com/gin-gonic/gin@v1.10.0/context.go:185 +0x2b fp=0xc0005c3718 sp=0xc0005c36f8 pc=0x7ff78ec584ab
github.com/ollama/ollama/server.(*Server).GenerateRoutes.allowedHostsMiddleware.func3(0xc000125400)
        github.com/ollama/ollama/server/routes.go:1110 +0x115 fp=0xc0005c3770 sp=0xc0005c3718 pc=0x7ff78f22dff5
github.com/gin-gonic/gin.(*Context).Next(...)
        github.com/gin-gonic/gin@v1.10.0/context.go:185
github.com/gin-gonic/gin.CustomRecoveryWithWriter.func1(0xc000125400)
        github.com/gin-gonic/gin@v1.10.0/recovery.go:102 +0x6f fp=0xc0005c37c0 sp=0xc0005c3770 pc=0x7ff78ec6636f
github.com/gin-gonic/gin.(*Context).Next(...)
        github.com/gin-gonic/gin@v1.10.0/context.go:185
github.com/gin-gonic/gin.LoggerWithConfig.func1(0xc000125400)
        github.com/gin-gonic/gin@v1.10.0/logger.go:249 +0xe5 fp=0xc0005c3978 sp=0xc0005c37c0 pc=0x7ff78ec654a5
github.com/gin-gonic/gin.(*Context).Next(...)
github.com/gin-gonic/gin@v1.10.0/context.go:185
github.com/gin-gonic/gin.(*Engine).handleHTTPRequest(0xc000612000, 0xc000125400)
        github.com/gin-gonic/gin@v1.10.0/gin.go:633 +0x892 fp=0xc0005c3ae0 sp=0xc0005c3978 pc=0x7ff78ec648d2
github.com/gin-gonic/gin.(*Engine).ServeHTTP(0xc000612000, {0x7ff78f899940, 0xc0000fa2a0}, 0xc0003d4500)
        github.com/gin-gonic/gin@v1.10.0/gin.go:589 +0x1b2 fp=0xc0005c3b18 sp=0xc0005c3ae0 pc=0x7ff78ec63e72
net/http.(*ServeMux).ServeHTTP(0x7ff78e651b85?, {0x7ff78f899940, 0xc0000fa2a0}, 0xc0003d4500)
        net/http/server.go:2747 +0x1ca fp=0xc0005c3b68 sp=0xc0005c3b18 pc=0x7ff78e9e92ca
net/http.serverHandler.ServeHTTP({0x7ff78f8963d0?}, {0x7ff78f899940?, 0xc0000fa2a0?}, 0x6?)
        net/http/server.go:3210 +0x8e fp=0xc0005c3b98 sp=0xc0005c3b68 pc=0x7ff78ea0682e
net/http.(*conn).serve(0xc0000f9cb0, {0x7ff78f89ba48, 0xc000516f60})
        net/http/server.go:2092 +0x5d0 fp=0xc0005c3fb8 sp=0xc0005c3b98 pc=0x7ff78e9e5d70
net/http.(*Server).Serve.gowrap3()
        net/http/server.go:3360 +0x28 fp=0xc0005c3fe0 sp=0xc0005c3fb8 pc=0x7ff78e9eb1c8
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0005c3fe8 sp=0xc0005c3fe0 pc=0x7ff78e6b8921
created by net/http.(*Server).Serve in goroutine 1
        net/http/server.go:3360 +0x485
goroutine 30 gp=0xc00043ec40 m=nil [IO wait]:
runtime.gopark(0x0?, 0xc000524f20?, 0xc8?, 0x4f?, 0xc000524fcc?)
        runtime/proc.go:424 +0xce fp=0xc00039fd20 sp=0xc00039fd00 pc=0x7ff78e6b03ee
runtime.netpollblock(0x4e4?, 0x8e648386?, 0xf7?)
        runtime/netpoll.go:575 +0xf7 fp=0xc00039fd58 sp=0xc00039fd20 pc=0x7ff78e674fb7
internal/poll.runtime_pollWait(0x2ba670fd9f8, 0x72)
        runtime/netpoll.go:351 +0x85 fp=0xc00039fd78 sp=0xc00039fd58 pc=0x7ff78e6af665
internal/poll.(*pollDesc).wait(0xc00039fdd8?, 0x7ff78e656085?, 0x0)
        internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00039fda0 sp=0xc00039fd78 pc=0x7ff78e744f07
internal/poll.execIO(0xc000524f20, 0x7ff78f75d248)
        internal/poll/fd_windows.go:177 +0x105 fp=0xc00039fe18 sp=0xc00039fda0 pc=0x7ff78e746345
internal/poll.(*FD).Read(0xc000524f08, {0xc000517061, 0x1, 0x1})
        internal/poll/fd_windows.go:438 +0x2a7 fp=0xc00039fec0 sp=0xc00039fe18 pc=0x7ff78e747047
net.(*netFD).Read(0xc000524f08, {0xc000517061?, 0xc00039ff48?, 0x7ff78e6b1d30?})
        net/fd_posix.go:55 +0x25 fp=0xc00039ff08 sp=0xc00039fec0 pc=0x7ff78e7b04e5
net.(*conn).Read(0xc000072898, {0xc000517061?, 0x0?, 0x7ff790155020?})
        net/net.go:189 +0x45 fp=0xc00039ff50 sp=0xc00039ff08 pc=0x7ff78e7bfac5
net.(*TCPConn).Read(0x7ff7900bbce0?, {0xc000517061?, 0x80?, 0x0?})
        <autogenerated>:1 +0x25 fp=0xc00039ff80 sp=0xc00039ff50 pc=0x7ff78e7d14e5
net/http.(*connReader).backgroundRead(0xc000517050)
        net/http/server.go:690 +0x37 fp=0xc00039ffc8 sp=0xc00039ff80 pc=0x7ff78e9e06f7
net/http.(*connReader).startBackgroundRead.gowrap2()
        net/http/server.go:686 +0x25 fp=0xc00039ffe0 sp=0xc00039ffc8 pc=0x7ff78e9e0625
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00039ffe8 sp=0xc00039ffe0 pc=0x7ff78e6b8921
created by net/http.(*connReader).startBackgroundRead in goroutine 40
        net/http/server.go:686 +0xb6
goroutine 11 gp=0xc000161880 m=nil [sleep]:
runtime.gopark(0x9f6ee0fd6a8?, 0x1?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000045d00 sp=0xc000045ce0 pc=0x7ff78e6b03ee
time.Sleep(0xee6b280)
        runtime/time.go:300 +0xf7 fp=0xc000045d38 sp=0xc000045d00 pc=0x7ff78e6b4777
github.com/ollama/ollama/llm.(*llmServer).WaitUntilRunning(0xc0001f5800, {0x7ff78f89ba80, 0xc000491bd0})
        github.com/ollama/ollama/llm/server.go:607 +0x10a fp=0xc000045ee0 sp=0xc000045d38 pc=0x7ff78ec9826a
github.com/ollama/ollama/server.(*Scheduler).load.func1()
        github.com/ollama/ollama/server/sched.go:454 +0x95 fp=0xc000045fe0 sp=0xc000045ee0 pc=0x7ff78f235535
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000045fe8 sp=0xc000045fe0 pc=0x7ff78e6b8921
created by github.com/ollama/ollama/server.(*Scheduler).load in goroutine 36
        github.com/ollama/ollama/server/sched.go:452 +0x7df
rax     0x700000000
rbx     0x1
rcx     0x7fff4db504c4
rdx     0x0
rdi     0x7ff79005cf80
rsi     0xc8000006
rbp     0x0
rsp     0xfa0bfff340
r8      0xfa0bfff2f8
r9      0x0
r10     0x0
r11     0x246
r12     0xc00020e020
r13     0x0
r14     0x7ff7901078b0
r15     0x3ffffe2000d1fdf
rip     0x7fff40a1105e
rflags  0x10246
cs      0x33
fs      0x53
gs      0x2b

OS

Windows

GPU

No response

CPU

AMD

Ollama version

0.5.7

Originally created by @liangkx19 on GitHub (Mar 17, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9803 ### What is the issue? 1、set OLLAMA_DEBUG=true && ollama.exe serve 2、ollama.exe run run deepseek-r1:1.5b => error ### Relevant log output ```shell 2025/03/17 11:17:26 routes.go:1187: INFO server config env="map[CUDA_VISIBLE_DEVICES:-1 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:true OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\\Ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-03-17T11:17:26.301+08:00 level=INFO source=images.go:432 msg="total blobs: 9" time=2025-03-17T11:17:26.316+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-03-17T11:17:26.321+08:00 level=INFO source=routes.go:1238 msg="Listening on 127.0.0.1:11434 (version 0.5.7)" time=2025-03-17T11:17:26.321+08:00 level=DEBUG source=common.go:80 msg="runners located" dir="D:\\Ollama\\lib\\ollama\\runners" time=2025-03-17T11:17:26.326+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu\\ollama_llama_server.exe" time=2025-03-17T11:17:26.327+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx\\ollama_llama_server.exe" time=2025-03-17T11:17:26.327+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx2\\ollama_llama_server.exe" time=2025-03-17T11:17:26.328+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11\\ollama_llama_server.exe" time=2025-03-17T11:17:26.328+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11_avx\\ollama_llama_server.exe" time=2025-03-17T11:17:26.329+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v12\\ollama_llama_server.exe" time=2025-03-17T11:17:26.329+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v12_avx\\ollama_llama_server.exe" time=2025-03-17T11:17:26.330+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_avx\\ollama_llama_server.exe" time=2025-03-17T11:17:26.330+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_v6.1\\ollama_llama_server.exe" time=2025-03-17T11:17:26.331+08:00 level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu_avx2 cuda_v11 cuda_v12 cpu cpu_avx cuda_v11_avx cuda_v12_avx rocm_avx rocm_v6.1]" time=2025-03-17T11:17:26.332+08:00 level=DEBUG source=routes.go:1268 msg="Override detection logic by setting OLLAMA_LLM_LIBRARY" time=2025-03-17T11:17:26.332+08:00 level=DEBUG source=sched.go:105 msg="starting llm scheduler" time=2025-03-17T11:17:26.333+08:00 level=INFO source=gpu.go:226 msg="looking for compatible GPUs" time=2025-03-17T11:17:26.333+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-03-17T11:17:26.333+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=6 efficiency=0 threads=12 time=2025-03-17T11:17:26.334+08:00 level=DEBUG source=gpu.go:99 msg="searching for GPU discovery libraries for NVIDIA" time=2025-03-17T11:17:26.336+08:00 level=DEBUG source=gpu.go:517 msg="Searching for GPU library" name=nvml.dll time=2025-03-17T11:17:26.337+08:00 level=DEBUG source=gpu.go:543 msg="gpu library search" globs="[D:\\Ollama\\lib\\ollama\\nvml.dll D:\\Ollama\\lib\\ollama\\nvml.dll C:\\Program Files\\Python39\\Scripts\\nvml.dll C:\\Program Files\\Python39\\nvml.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\nvml.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\nvml.dll C:\\Oracle\\product\\11.2.0\\client_2\\bin\\nvml.dll C:\\Oracle\\product\\11.2.0\\client_1\\nvml.dll C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath\\nvml.dll C:\\windows\\system32\\nvml.dll C:\\windows\\nvml.dll C:\\windows\\System32\\Wbem\\nvml.dll C:\\windows\\System32\\WindowsPowerShell\\v1.0\\nvml.dll C:\\windows\\System32\\OpenSSH\\nvml.dll C:\\Program Files (x86)\\Enterprise Vault\\EVClient\\x64\\nvml.dll C:\\Program Files (x86)\\Java\\jre6\\bin\\nvml.dll C:\\Program Files\\Microsoft VS Code\\bin\\nvml.dll C:\\Program Files\\TortoiseSVN\\bin\\nvml.dll C:\\Program Files\\nodejs\\nvml.dll C:\\Program Files\\Citrix\\System32\\nvml.dll C:\\Program Files\\Citrix\\ICAService\\nvml.dll C:\\Program Files\\Git\\cmd\\nvml.dll C:\\Users\\Test\\AppData\\Local\\Microsoft\\WindowsApps\\nvml.dll C:\\Users\\localadmin\\AppData\\Roaming\\npm\\nvml.dll C:\\Users\\Test\\AppData\\Local\\ms-playwright\\chromium-1091\\chromium-win64\\chrome-win\\chrome.exe\\nvml.dll C:\\Users\\Test\\AppData\\Roaming\\Python\\Python39\\Scripts\\nvml.dll D:\\Ollama\\nvml.dll c:\\Windows\\System32\\nvml.dll]" time=2025-03-17T11:17:26.344+08:00 level=DEBUG source=gpu.go:576 msg="discovered GPU libraries" paths=[] time=2025-03-17T11:17:26.337+08:00 level=DEBUG source=gpu.go:543 msg="gpu library search" globs="[D:\\Ollama\\lib\\ollama\\nvml.dll D:\\Ollama\\lib\\ollama\\nvml.dll C:\\Program Files\\Python39\\Scripts\\nvml.dll C:\\Program Files\\Python39\\nvml.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\nvml.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\nvml.dll C:\\Oracle\\product\\11.2.0\\client_2\\bin\\nvml.dll C:\\Oracle\\product\\11.2.0\\client_1\\nvml.dll C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath\\nvml.dll C:\\windows\\system32\\nvml.dll C:\\windows\\nvml.dll C:\\windows\\System32\\Wbem\\nvml.dll C:\\windows\\System32\\WindowsPowerShell\\v1.0\\nvml.dll C:\\windows\\System32\\OpenSSH\\nvml.dll C:\\Program Files (x86)\\Enterprise Vault\\EVClient\\x64\\nvml.dll C:\\Program Files (x86)\\Java\\jre6\\bin\\nvml.dll C:\\Program Files\\Microsoft VS Code\\bin\\nvml.dll C:\\Program Files\\TortoiseSVN\\bin\\nvml.dll C:\\Program Files\\nodejs\\nvml.dll C:\\Program Files\\Citrix\\System32\\nvml.dll C:\\Program Files\\Citrix\\ICAService\\nvml.dll C:\\Program Files\\Git\\cmd\\nvml.dll C:\\Users\\Test\\AppData\\Local\\Microsoft\\WindowsApps\\nvml.dll C:\\Users\\localadmin\\AppData\\Roaming\\npm\\nvml.dll C:\\Users\\Test\\AppData\\Local\\ms-playwright\\chromium-1091\\chromium-win64\\chrome-win\\chrome.exe\\nvml.dll C:\\Users\\Test\\AppData\\Roaming\\Python\\Python39\\Scripts\\nvml.dll D:\\Ollama\\nvml.dll c:\\Windows\\System32\\nvml.dll]" time=2025-03-17T11:17:26.344+08:00 level=DEBUG source=gpu.go:576 msg="discovered GPU libraries" paths=[] time=2025-03-17T11:17:26.345+08:00 level=DEBUG source=gpu.go:517 msg="Searching for GPU library" name=nvcuda.dll time=2025-03-17T11:17:26.346+08:00 level=DEBUG source=gpu.go:543 msg="gpu library search" globs="[D:\\Ollama\\lib\\ollama\\nvcuda.dll D:\\Ollama\\lib\\ollama\\nvcuda.dll C:\\Program Files\\Python39\\Scripts\\nvcuda.dll C:\\Program Files\\Python39\\nvcuda.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\nvcuda.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\nvcuda.dll C:\\Oracle\\product\\11.2.0\\client_2\\bin\\nvcuda.dll C:\\Oracle\\product\\11.2.0\\client_1\\nvcuda.dll C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath\\nvcuda.dll C:\\windows\\system32\\nvcuda.dll C:\\windows\\nvcuda.dll C:\\windows\\System32\\Wbem\\nvcuda.dll C:\\windows\\System32\\WindowsPowerShell\\v1.0\\nvcuda.dll C:\\windows\\System32\\OpenSSH\\nvcuda.dll C:\\Program Files (x86)\\Enterprise Vault\\EVClient\\x64\\nvcuda.dll C:\\Program Files (x86)\\Java\\jre6\\bin\\nvcuda.dll C:\\Program Files\\Microsoft VS Code\\bin\\nvcuda.dll C:\\Program Files\\TortoiseSVN\\bin\\nvcuda.dll C:\\Program Files\\nodejs\\nvcuda.dll C:\\Program Files\\Citrix\\System32\\nvcuda.dll C:\\Program Files\\Citrix\\ICAService\\nvcuda.dll C:\\Program Files\\Git\\cmd\\nvcuda.dll C:\\Users\\Test\\AppData\\Local\\Microsoft\\WindowsApps\\nvcuda.dll C:\\Users\\localadmin\\AppData\\Roaming\\npm\\nvcuda.dll C:\\Users\\Test\\AppData\\Local\\ms-playwright\\chromium-1091\\chromium-win64\\chrome-win\\chrome.exe\\nvcuda.dll C:\\Users\\Test\\AppData\\Roaming\\Python\\Python39\\Scripts\\nvcuda.dll D:\\Ollama\\nvcuda.dll c:\\windows\\system*\\nvcuda.dll]" time=2025-03-17T11:17:26.357+08:00 level=DEBUG source=gpu.go:576 msg="discovered GPU libraries" paths=[C:\windows\system32\nvcuda.dll] initializing C:\windows\system32\nvcuda.dll dlsym: cuInit - 00007FFED4855010 dlsym: cuDriverGetVersion - 00007FFED485AB91 dlsym: cuDeviceGetCount - 00007FFED4856C21 dlsym: cuDeviceGet - 00007FFED4855A15 dlsym: cuDeviceGetAttribute - 00007FFED485970A dlerr: 找不到指定的程序。 time=2025-03-17T11:17:26.384+08:00 level=INFO source=gpu.go:630 msg="Unable to load cudart library C:\\windows\\system32\\nvcuda.dll: symbol lookup for cuDeviceGetUuid failed: \xd5?\xbb\xb5\xbd?\xb6\xa8\xb5?\xcc\xd0\xf2\xa1\xa3\r\n" time=2025-03-17T11:17:26.385+08:00 level=DEBUG source=gpu.go:517 msg="Searching for GPU library" name=cudart64_*.dll time=2025-03-17T11:17:26.386+08:00 level=DEBUG source=gpu.go:543 msg="gpu library search" globs="[D:\\Ollama\\lib\\ollama\\cudart64_*.dll D:\\Ollama\\lib\\ollama\\cudart64_*.dll C:\\Program Files\\Python39\\Scripts\\cudart64_*.dll C:\\Program Files\\Python39\\cudart64_*.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\cudart64_*.dll C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\cudart64_*.dll C:\\Oracle\\product\\11.2.0\\client_2\\bin\\cudart64_*.dll C:\\Oracle\\product\\11.2.0\\client_1\\cudart64_*.dll C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath\\cudart64_*.dll C:\\windows\\system32\\cudart64_*.dll C:\\windows\\cudart64_*.dll C:\\windows\\System32\\Wbem\\cudart64_*.dll C:\\windows\\System32\\WindowsPowerShell\\v1.0\\cudart64_*.dll C:\\windows\\System32\\OpenSSH\\cudart64_*.dll C:\\Program Files (x86)\\Enterprise Vault\\EVClient\\x64\\cudart64_*.dll C:\\Program Files (x86)\\Java\\jre6\\bin\\cudart64_*.dll C:\\Program Files\\Microsoft VS Code\\bin\\cudart64_*.dll C:\\Program Files\\TortoiseSVN\\bin\\cudart64_*.dll C:\\Program Files\\nodejs\\cudart64_*.dll C:\\Program Files\\Citrix\\System32\\cudart64_*.dll C:\\Program Files\\Git\\cmd\\cudart64_*.dll C:\\Users\\Test\\AppData\\Local\\Microsoft\\WindowsApps\\cudart64_*.dll C:\\Users\\localadmin\\AppData\\Roaming\\npm\\cudart64_*.dll C:\\Users\\Test\\AppData\\Local\\ms-playwright\\chromium-1091\\chromium-win64\\chrome-win\\chrome.exe\\cudart64_*.dllC:\\Users\\Test\\AppData\\Roaming\\Python\\Python39\\Scripts\\cudart64_*.dll D:\\Ollama\\cudart64_*.dll C:\\Users\\Test\\AppData\\Local\\Programs\\Ollama\\cudart64_*.dll D:\\Ollama\\lib\\ollama\\cudart64_*.dll D:\\Ollama\\lib\\ollama\\cudart64_*.dll c:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v*\\bin\\cudart64_*.dll]" time=2025-03-17T11:17:26.444+08:00 level=DEBUG source=gpu.go:576 msg="discovered GPU libraries" paths="[D:\\Ollama\\lib\\ollama\\cudart64_110.dll D:\\Ollama\\lib\\ollama\\cudart64_12.dll]" cudaSetDevice err: 100 time=2025-03-17T11:17:26.878+08:00 level=DEBUG source=gpu.go:592 msg="Unable to load cudart library D:\\Ollama\\lib\\ollama\\cudart64_110.dll: cudart init failure: 100" cudaSetDevice err: 35 time=2025-03-17T11:17:26.883+08:00 level=DEBUG source=gpu.go:592 msg="Unable to load cudart library D:\\Ollama\\lib\\ollama\\cudart64_12.dll: your nvidia driver is too old or missing. If you have a CUDA GPU please upgrade to run ollama" time=2025-03-17T11:17:26.886+08:00 level=DEBUG source=amd_windows.go:35 msg="unable to load amdhip64_6.dll, please make sure to upgrade to the latest amd driver: The specified module could not be found." time=2025-03-17T11:17:26.886+08:00 level=INFO source=gpu.go:392 msg="no compatible GPUs were discovered" time=2025-03-17T11:17:26.887+08:00 level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="15.9 GiB" available="8.3 GiB" time=2025-03-17T11:55:42.710+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu\\ollama_llama_server.exe" time=2025-03-17T11:55:42.711+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx\\ollama_llama_server.exe" time=2025-03-17T11:55:42.711+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx2\\ollama_llama_server.exe" time=2025-03-17T11:55:42.712+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11\\ollama_llama_server.exe" time=2025-03-17T11:55:42.712+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11_avx\\ollama_llama_server.exe" time=2025-03-17T11:55:42.713+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v12\\ollama_llama_server.exe" time=2025-03-17T11:55:42.714+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_avx\\ollama_llama_server.exe" time=2025-03-17T11:55:42.715+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_v6.1\\ollama_llama_server.exe" time=2025-03-17T11:55:42.716+08:00 level=DEBUG source=memory.go:107 msg=evaluating library=cpu gpu_count=1 available="[8.3 GiB]" time=2025-03-17T11:55:42.718+08:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=29 layers.offload=0 layers.split="" memory.available="[8.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.5 GiB" memory.required.partial="0 B" memory.required.kv="224.0 MiB" memory.required.allocations="[1.5 GiB]" memory.weights.total="976.1 MiB" memory.weights.repeating="793.5 MiB" memory.weights.nonrepeating="182.6 MiB" memory.graph.full="299.8 MiB" memory.graph.partial="482.3 MiB" time=2025-03-17T11:55:42.722+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu\\ollama_llama_server.exe" time=2025-03-17T11:55:42.722+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx\\ollama_llama_server.exe" time=2025-03-17T11:55:42.723+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx2\\ollama_llama_server.exe" time=2025-03-17T11:55:42.723+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11\\ollama_llama_server.exe" time=2025-03-17T11:55:42.724+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v11_avx\\ollama_llama_server.exe" time=2025-03-17T11:55:42.729+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v12\\ollama_llama_server.exe" time=2025-03-17T11:55:42.729+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\cuda_v12_avx\\ollama_llama_server.exe" time=2025-03-17T11:55:42.730+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_avx\\ollama_llama_server.exe" time=2025-03-17T11:55:42.730+08:00 level=DEBUG source=common.go:124 msg="availableServers : found" file="D:\\Ollama\\lib\\ollama\\runners\\rocm_v6.1\\ollama_llama_server.exe" time=2025-03-17T11:55:42.747+08:00 level=DEBUG source=gpu.go:713 msg="no filter required for library cpu" time=2025-03-17T11:55:42.747+08:00 level=INFO source=server.go:376 msg="starting llama server" cmd="D:\\Ollama\\lib\\ollama\\runners\\cpu_avx2\\ollama_llama_server.exe runner --model D:\\Ollama\\models\\blobs\\sha256-aabd4debf0c8f08881923f2c25fc0fdeed24435271c2b3e92c4af36704040dbc --ctx-size 8192 --batch-size 512 --verbose --threads 6 --no-mmap --parallel 4 --port 8510" time=2025-03-17T11:55:42.748+08:00 level=DEBUG source=server.go:393 msg=subprocess environment="[PATH=D:\\Ollama\\lib\\ollama;D:\\Ollama\\lib\\ollama;D:\\Ollama\\lib\\ollama\\runners\\cpu_avx2;C:\\Program Files\\Python39\\Scripts\\;C:\\Program Files\\Python39\\;C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\;C:\\windows\\system32\\config\\systemprofile\\AppData\\Local\\Programs\\Python\\Python39\\;C:\\Oracle\\product\\11.2.0\\client_2\\bin;C:\\Oracle\\product\\11.2.0\\client_1;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\windows\\system32;C:\\windows;C:\\windows\\System32\\Wbem;C:\\windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\windows\\System32\\OpenSSH\\;C:\\Program Files (x86)\\Enterprise Vault\\EVClient\\x64\\;C:\\Program Files (x86)\\Java\\jre6\\bin;C:\\Program Files\\Microsoft VS Code\\bin;C:\\Program Files\\TortoiseSVN\\bin;C:\\Program Files\\nodejs\\;C:\\Program Files\\Citrix\\System32\\;C:\\Program Files\\Citrix\\ICAService\\;C:\\Program Files\\Git\\cmd;C:\\Users\\Test\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\localadmin\\AppData\\Roaming\\npm;C:\\Users\\Test\\AppData\\Local\\ms-playwright\\chromium-1091\\chromium-win64\\chrome-win\\chrome.exe;C:\\Users\\Test\\AppData\\Roaming\\Python\\Python39\\Scripts;]" time=2025-03-17T11:55:42.773+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-03-17T11:55:42.773+08:00 level=INFO source=server.go:555 msg="waiting for llama runner to start responding" Exception 0xc0000006 0x0 0x700000000 0x7fff40a1105e PC=0x7fff40a1105e signal arrived during external code execution runtime.cgocall(0x7ff78e6ba0e0, 0xc000438b30) runtime/cgocall.go:167 +0x3e fp=0xc0005c6d08 sp=0xc0005c6ca0 pc=0x7ff78e6a9c3e runtime.syscall_syscalln(0xc0005c6da8?, 0x5d0?, {0xc0005c6d50?, 0x0?, 0xc000438808?}) runtime/syscall_windows.go:521 +0x4e fp=0xc0005c6d28 sp=0xc0005c6d08 pc=0x7ff78e698f2e syscall.Syscall9(0x6?, 0xc0005c6e08?, 0x7ff78e6ddc48?, 0x7ff7900e4660?, 0xc000161c00?, 0x200000003?, 0x0?, 0x0?, 0xc000161c00?, 0x0, ...) runtime/syscall_windows.go:469 +0x57 fp=0xc0005c6da8 sp=0xc0005c6d28 pc=0x7ff78e6b4597 syscall.WSAIoctl(0x5d0, 0xc8000006, 0x7ff78e6ba0e0?, 0x10, 0x0?, 0x8, 0x7fff4b905b30?, 0x9?, 0x0) syscall/zsyscall_windows.go:1277 +0xd2 fp=0xc0005c6e38 sp=0xc0005c6da8 pc=0x7ff78e6dca72 syscall.LoadConnectEx.func1() syscall/syscall_windows.go:1051 +0xbf fp=0xc0005c6eb0 sp=0xc0005c6e38 pc=0x7ff78e6ddd9f sync.(*Once).doSlow(0x4?, 0x0?) sync/once.go:76 +0xb4 fp=0xc0005c6f10 sp=0xc0005c6eb0 pc=0x7ff78e6c8294 sync.(*Once).Do(...) sync/once.go:67 syscall.LoadConnectEx() syscall/syscall_windows.go:1043 +0x2c fp=0xc0005c6f30 sp=0xc0005c6f10 pc=0x7ff78e6d616c syscall.ConnectEx(0x5b4, {0x7ff78f893060, 0xc00022c020}, 0x0, 0x0, 0x0, 0xc000524368) syscall/syscall_windows.go:1075 +0x3f fp=0xc0005c6f88 sp=0xc0005c6f30 pc=0x7ff78e6d62df internal/poll.(*FD).ConnectEx.func1(0xc0005c7058?) internal/poll/fd_windows.go:937 +0x3e fp=0xc0005c6fd0 sp=0xc0005c6f88 pc=0x7ff78e74ef9e internal/poll.execIO(0xc000524368, 0x7ff78f75d238) internal/poll/fd_windows.go:161 +0x7b fp=0xc0005c7048 sp=0xc0005c6fd0 pc=0x7ff78e7462bb internal/poll.(*FD).ConnectEx(0x5b4?, {0x7ff78f893060?, 0xc00022c020?}) internal/poll/fd_windows.go:936 +0x54 fp=0xc0005c7068 sp=0xc0005c7048 pc=0x7ff78e74a8d4 net.(*netFD).connect(0xc000524288, {0x7ff78f89baf0, 0xc0005aeaf0}, {0x0, 0x0?}, {0x7ff78f893060, 0xc00022c020}) net/fd_windows.go:149 +0x4dd fp=0xc0005c71a8 sp=0xc0005c7068 pc=0x7ff78e7b1bdd net.(*netFD).dial(0xc000524288, {0x7ff78f89baf0, 0xc0005aeaf0}, {0x7ff78f89f2a0?, 0x0?}, {0x7ff78f89f2a0, 0xc000782de0}, 0x7ff78e7b558b?) net/sock_posix.go:124 +0x3c5 fp=0xc0005c7280 sp=0xc0005c71a8 pc=0x7ff78e7c4585 net.socket({0x7ff78f89baf0, 0xc0005aeaf0}, {0x7ff78f6d96b8, 0x3}, 0x2, 0x1, 0x20?, 0x0, {0x7ff78f89f2a0, 0x0}, ...) net/sock_posix.go:70 +0x2af fp=0xc0005c7328 sp=0xc0005c7280usage: D:\Ollama\lib\ollama\runners\cpu_avx2\ollama_llama_server.exe [options] e pc= rror: unknown argument: runner 0x7ff78e7c40cfoptions: -h, --help show this help message and exit net.internetSocket -v, --verbose verbose output (default: disabled) ( -t N, --threads N number of threads to use during computation (default: -1) { -tb N, --threads-batch N number of threads to use during batch and prompt processing (default: same as --threads) 0x7ff78f89baf0 --threads-http N number of threads in the http server pool to process requests (default: max(hardware concurrency - 1, --parallel N + 2)) , -c N, --ctx-size N size of the prompt context (default: 0) 0xc0005aeaf0 --rope-scaling {none,linear,yarn} } RoPE frequency scaling method, defaults to linear unless specified by the model , --rope-freq-base N RoPE base frequency (default: loaded from model) { --rope-freq-scale N RoPE frequency scaling factor, expands context by a factor of 1/N --yarn-ext-factor N YaRN: extrapolation mix factor (default: 1.0, 0.0 = full interpolation) --yarn-attn-factor N YaRN: scale sqrt(t) or attention magnitude (default: 1.0) 0x7ff78f6d96b8 --yarn-beta-slow N YaRN: high correction dim or alpha (default: 1.0) , --yarn-beta-fast N YaRN: low correction dim or beta (default: 32.0) 0x3 --pooling {none,mean,cls} pooling type for embeddings, use model default if unspecified } -b N, --batch-size N batch size for prompt processing (default: 2048) for memory key+value (default: disabled) { not recommended: doubles context memory required and no measurable increase in quality 0x7ff78f89f2a0 --mlock force system to keep model in RAM rather than swapping or compressing , --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock) --numa TYPE attempt optimizations that help on some NUMA systems 0x0 - distribute: spread execution evenly over all nodes } - isolate: only spawn threads on CPUs on the node that execution started on , - numactl: use the CPU map provided my numactl { -m FNAME, --model FNAME 0x7ff78f89f2a0 model path (default: ) -a ALIAS, --alias ALIAS ? set an alias for the model, will be added as `model` field in completion response , --lora FNAME apply LoRA adapter (implies --no-mmap) 0xc000782de0 --lora-base FNAME optional model to use as a base for the layers modified by the LoRA adapter ?} --host ip address to listen (default (default: 127.0.0.1) , --port PORT port to listen (default (default: 8080) 0x1 --path PUBLIC_PATH path from which to serve static files (default examples/server/public) , --api-key API_KEY optional api key to enhance server security. If set, requests must include this key for access. 0x0 --api-key-file FNAME path to file containing api keys delimited by new lines. If set, requests must include one of the keys for access. , ...) -to N, --timeout N server read/write timeout in seconds (default: 600) net/ipsock_posix.go --embedding enable embedding vector output (default: disabled) : -np N, --parallel N number of slots for process requests (default: 1) 167 + -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: disabled) 0x1e5 -fa, --flash-attn enable Flash Attention (default: disabled) fp= -spf FNAME, --system-prompt-file FNAME 0xc0005c73b0 sp= set a file to load a system prompt (initial prompt of all slots), this is useful for chat applications. 0xc0005c7328 -ctk TYPE, --cache-type-k TYPE pc= KV cache data type for K (default: f16) 0x7ff78e7bb425 -ctv TYPE, --cache-type-v TYPE KV cache data type for V (default: f16) net.(*sysDialer).doDialTCPProto --mmproj MMPROJ_FILE path to a multimodal projector file for LLaVA. ( --log-format log output format: json or text (default: json) 0xc000000480 --log-disable disables logging to a file. , {0x7ff78f89baf0, 0xc0005aeaf0 --slots-endpoint-disable disables slots monitoring endpoint. } --metrics enable prometheus compatible metrics endpoint (default: disabled). , 0x0 -n, --n-predict maximum tokens to predict (default: -1) , --override-kv KEY=TYPE:VALUE 0xc000782de0 advanced option to override model metadata by key. may be specified multiple times. , types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false 0x0) -gan N, --grp-attn-n N set the group attention factor to extend context size through self-extend(default: 1=disabled), used together with group attention width `--grp-attn-w` net/tcpsock_posix.go -gaw N, --grp-attn-w N set the group attention width to extend context size through self-extend(default: 512), used together with group attention factor `--grp-attn-n` : --chat-template JINJA_TEMPLATE 85 set custom jinja chat template (default: template taken from model's metadata) + Note: only commonly used templates are accepted, since we don't have jinja parser 0xec fp=0xc0005c7460 sp=0xc0005c73b0 pc=0x7ff78e7c806c net.(*sysDialer).doDialTCP(...) net/tcpsock_posix.go:75 net.(*sysDialer).dialTCP(0xc0006834c8?, {0x7ff78f89baf0?, 0xc0005aeaf0?}, 0x7ff78f5a0400?, 0xc000683538?) net/tcpsock_posix.go:71 +0x69 fp=0xc0005c74a0 sp=0xc0005c7460 pc=0x7ff78e7c7f09 net.(*sysDialer).dialSingle(0xc000000480, {0x7ff78f89baf0, 0xc0005aeaf0}, {0x7ff78f8962b8, 0xc000782de0}) net/dial.go:670 +0x27d fp=0xc0005c7570 sp=0xc0005c74a0 pc=0x7ff78e7a975d net.(*sysDialer).dialSerial(0xc000000480, {0x7ff78f89baf0, 0xc0005aeaf0}, {0xc00017cb60?, 0x1, 0xc000782db0?}) net/dial.go:635 +0x24e fp=0xc0005c7678 sp=0xc0005c7570 pc=0x7ff78e7a908e net.(*sysDialer).dialParallel(0xc00017cb40?, {0x7ff78f89baf0?, 0xc0005aeaf0?}, {0xc00017cb60?, 0xc0005aeaf0?, 0x7ff78f6da33f?}, {0x0?, 0x7ff78f6d96b8?, 0x10?}) net/dial.go:536 +0x3a7 fp=0xc0005c7890 sp=0xc0005c7678 pc=0x7ff78e7a8767 net.(*Dialer).DialContext(0xc0000f9320, {0x7ff78f89ba80, 0xc000882320}, {0x7ff78f6d96b8, 0x3}, {0xc0007809e0, 0xe}) net/dial.go:527 +0x6a5 fp=0xc0005c79b0 sp=0xc0005c7890 pc=0x7ff78e7a81e5 net.(*Dialer).DialContext-fm({0x7ff78f89ba80?, 0xc000882320?}, {0x7ff78f6d96b8?, 0x7ff790155020?}, {0xc0007809e0?, 0xc000683a50?}) <autogenerated>:1 +0x49 fp=0xc0005c79f8 sp=0xc0005c79b0 pc=0x7ff78ea13f49 net/http.(*Transport).dial(0x0?, {0x7ff78f89ba80?, 0xc000882320?}, {0x7ff78f6d96b8?, 0x0?}, {0xc0007809e0?, 0x0?}) net/http/transport.go:1226 +0xd2 fp=0xc0005c7a60 sp=0xc0005c79f8 pc=0x7ff78e9fa112 net/http.(*Transport).dialConn(0x7ff7900f8b20, {0x7ff78f89ba80, 0xc000882320}, {{}, 0x0, {0xc00037c8e0, 0x4}, {0xc0007809e0, 0xe}, 0x0}) net/http/transport.go:1728 +0x7e5 fp=0xc0005c7ed8 sp=0xc0005c7a60 pc=0x7ff78e9fd265 net/http.(*Transport).dialConnFor(0x7ff7900f8b20, 0xc000151a20) net/http/transport.go:1563 +0xb8 fp=0xc0005c7f88 sp=0xc0005c7ed8 pc=0x7ff78e9fbd58 net/http.(*Transport).startDialConnForLocked.func1() net/http/transport.go:1545 +0x35 fp=0xc0005c7fe0 sp=0xc0005c7f88 pc=0x7ff78e9fbb95 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0005c7fe8 sp=0xc0005c7fe0 pc=0x7ff78e6b8921 created by net/http.(*Transport).startDialConnForLocked in goroutine 11 net/http/transport.go:1544 +0x117 goroutine 1 gp=0xc000068000 m=nil [IO wait]: runtime.gopark(0x7ff78e6ba0e0?, 0x7ff7900e3e20?, 0x20?, 0x40?, 0xc0005240cc?) runtime/proc.go:424 +0xce fp=0xc0006875f0 sp=0xc0006875d0 pc=0x7ff78e6b03ee runtime.netpollblock(0x268?, 0x8e648386?, 0xf7?) runtime/netpoll.go:575 +0xf7 fp=0xc000687628 sp=0xc0006875f0 pc=0x7ff78e674fb7 internal/poll.runtime_pollWait(0x2ba670fdb10, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc000687648 sp=0xc000687628 pc=0x7ff78e6af665 internal/poll.(*pollDesc).wait(0x7ff78e7438d5?, 0x7ff78e6aae9d?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000687670 sp=0xc000687648 pc=0x7ff78e744f07 internal/poll.execIO(0xc000524020, 0xc0003ad718) internal/poll/fd_windows.go:177 +0x105 fp=0xc0006876e8 sp=0xc000687670 pc=0x7ff78e746345 internal/poll.(*FD).acceptOne(0xc000524008, 0x40c, {0xc0001705a0?, 0xc0003ad778?, 0x7ff78e74e0c5?}, 0xc0003ad7ac?) internal/poll/fd_windows.go:946 +0x65 fp=0xc000687748 sp=0xc0006876e8 pc=0x7ff78e74a985 internal/poll.(*FD).Accept(0xc000524008, 0xc0006878f8) internal/poll/fd_windows.go:980 +0x1b6 fp=0xc000687800 sp=0xc000687748 pc=0x7ff78e74acb6 net.(*netFD).accept(0xc000524008) net/fd_windows.go:182 +0x4b fp=0xc000687918 sp=0xc000687800 pc=0x7ff78e7b23cb net.(*TCPListener).accept(0xc000248080) net/tcpsock_posix.go:159 +0x1e fp=0xc000687968 sp=0xc000687918 pc=0x7ff78e7c853e net.(*TCPListener).Accept(0xc000248080) net/tcpsock.go:372 +0x30 fp=0xc000687998 sp=0xc000687968 pc=0x7ff78e7c72f0 net/http.(*onceCloseListener).Accept(0xc0000f9cb0?) <autogenerated>:1 +0x24 fp=0xc0006879b0 sp=0xc000687998 pc=0x7ff78ea12e44 net/http.(*Server).Serve(0xc0006002d0, {0x7ff78f899760, 0xc000248080}) net/http/server.go:3330 +0x30c fp=0xc000687ae0 sp=0xc0006879b0 pc=0x7ff78e9eadcc github.com/ollama/ollama/server.Serve({0x7ff78f899760, 0xc000248080}) github.com/ollama/ollama/server/routes.go:1277 +0x8cc fp=0xc000687d18 sp=0xc000687ae0 pc=0x7ff78f22e96c github.com/ollama/ollama/cmd.RunServer(0xc000124900?, {0x7ff790155020?, 0x4?, 0x7ff78f6da1ef?}) github.com/ollama/ollama/cmd/cmd.go:1033 +0x4a fp=0xc000687d58 sp=0xc000687d18 pc=0x7ff78f25daaa github.com/spf13/cobra.(*Command).execute(0xc0001de608, {0x7ff790155020, 0x0, 0x0}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x862 fp=0xc000687e78 sp=0xc000687d58 pc=0x7ff78e82c122 github.com/spf13/cobra.(*Command).ExecuteC(0xc0001e9508) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000687f30 sp=0xc000687e78 pc=0x7ff78e82c965 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=0xc000687f50 sp=0xc000687f30 pc=0x7ff78f265c8d runtime.main() runtime/proc.go:272 +0x27d fp=0xc000687fe0 sp=0xc000687f50 pc=0x7ff78e67dfbd runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000687fe8 sp=0xc000687fe0 pc=0x7ff78e6b8921 goroutine 2 gp=0xc000068700 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00006bfa8 sp=0xc00006bf88 pc=0x7ff78e6b03ee runtime.goparkunlock(...) runtime/proc.go:430 runtime.forcegchelper() runtime/proc.go:337 +0xb8 fp=0xc00006bfe0 sp=0xc00006bfa8 pc=0x7ff78e67e2d8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006bfe8 sp=0xc00006bfe0 pc=0x7ff78e6b8921 created by runtime.init.7 in goroutine 1 runtime/proc.go:325 +0x1a goroutine 3 gp=0xc000068a80 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00006df80 sp=0xc00006df60 pc=0x7ff78e6b03ee runtime.goparkunlock(...) runtime/proc.go:430 runtime.bgsweep(0xc00007a000) runtime/mgcsweep.go:317 +0xdf fp=0xc00006dfc8 sp=0xc00006df80 pc=0x7ff78e666fbf runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc00006dfe0 sp=0xc00006dfc8 pc=0x7ff78e65b5e5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006dfe8 sp=0xc00006dfe0 pc=0x7ff78e6b8921 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000068c40 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x7ff78f888818?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000085f78 sp=0xc000085f58 pc=0x7ff78e6b03ee runtime.goparkunlock(...) runtime/proc.go:430 runtime.(*scavengerState).park(0x7ff790108560) runtime/mgcscavenge.go:425 +0x49 fp=0xc000085fa8 sp=0xc000085f78 pc=0x7ff78e664989 runtime.bgscavenge(0xc00007a000) runtime/mgcscavenge.go:658 +0x59 fp=0xc000085fc8 sp=0xc000085fa8 pc=0x7ff78e664f19 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc000085fe0 sp=0xc000085fc8 pc=0x7ff78e65b585 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff78e6b8921 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 5 gp=0xc000069180 m=nil [finalizer wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000087e20 sp=0xc000087e00 pc=0x7ff78e6b03ee runtime.runfinq() runtime/mfinal.go:193 +0x107 fp=0xc000087fe0 sp=0xc000087e20 pc=0x7ff78e65a6a7 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000087fe8 sp=0xc000087fe0 pc=0x7ff78e6b8921 created by runtime.createfing in goroutine 1 runtime/mfinal.go:163 +0x3d goroutine 6 gp=0xc000160a80 m=nil [chan receive]: runtime.gopark(0xc00006ff60?, 0x7ff78e79be85?, 0x10?, 0xe8?, 0x7ff78f8b0080?) runtime/proc.go:424 +0xce fp=0xc00006ff18 sp=0xc00006fef8 pc=0x7ff78e6b03ee runtime.chanrecv(0xc00007e310, 0x0, 0x1) runtime/chan.go:639 +0x41e fp=0xc00006ff90 sp=0xc00006ff18 pc=0x7ff78e64acbe time=2025-03-17T11:55:42.975+08:00 level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server not responding" runtime.chanrecv1(0x7ff78e67e120?, 0xc00006ff76?) runtime/chan.go:489 +0x12 fp=0xc00006ffb8 sp=0xc00006ff90 pc=0x7ff78e64a872 runtime.unique_runtime_registerUniqueMapCleanup.func1(...) runtime/mgc.go:1781 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1784 +0x2f fp=0xc00006ffe0 sp=0xc00006ffb8 pc=0x7ff78e65e6cf runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006ffe8 sp=0xc00006ffe0 pc=0x7ff78e6b8921 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1779 +0x96 goroutine 18 gp=0xc000208380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000081f38 sp=0xc000081f18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc000081fc8 sp=0xc000081f38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000081fe0 sp=0xc000081fc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 19 gp=0xc000208540 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000083f38 sp=0xc000083f18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc000083fc8 sp=0xc000083f38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 20 gp=0xc000208700 m=nil [GC worker (idle)]: runtime.gopark(0x9f6dea6b13c?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00041df38 sp=0xc00041df18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc00041dfc8 sp=0xc00041df38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00041dfe0 sp=0xc00041dfc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00041dfe8 sp=0xc00041dfe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 21 gp=0xc0002088c0 m=nil [GC worker (idle)]: runtime.gopark(0x9f6dea6b13c?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00041ff38 sp=0xc00041ff18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc00041ffc8 sp=0xc00041ff38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00041ffe0 sp=0xc00041ffc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00041ffe8 sp=0xc00041ffe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 22 gp=0xc000208a80 m=nil [GC worker (idle)]: runtime.gopark(0x9f6dea6b13c?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000419f38 sp=0xc000419f18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc000419fc8 sp=0xc000419f38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000419fe0 sp=0xc000419fc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000419fe8 sp=0xc000419fe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 23 gp=0xc000208c40 m=nil [GC worker (idle)]: runtime.gopark(0x9f6dea6b13c?, 0x3?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00041bf38 sp=0xc00041bf18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc00041bfc8 sp=0xc00041bf38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00041bfe0 sp=0xc00041bfc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00041bfe8 sp=0xc00041bfe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 24 gp=0xc000208e00 m=nil [GC worker (idle)]: runtime.gopark(0x9f6dea6b13c?, 0x1?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000425f38 sp=0xc000425f18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc000425fc8 sp=0xc000425f38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000425fe0 sp=0xc000425fc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000425fe8 sp=0xc000425fe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 25 gp=0xc000208fc0 m=nil [GC worker (idle)]: runtime.gopark(0x9f6dea6b13c?, 0x3?, 0x70?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000427f38 sp=0xc000427f18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc000427fc8 sp=0xc000427f38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000427fe0 sp=0xc000427fc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000427fe8 sp=0xc000427fe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 26 gp=0xc000209180 m=nil [GC worker (idle)]: runtime.gopark(0x7ff790157040?, 0x1?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000421f38 sp=0xc000421f18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc000421fc8 sp=0xc000421f38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000421fe0 sp=0xc000421fc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000421fe8 sp=0xc000421fe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 27 gp=0xc000209340 m=nil [GC worker (idle)]: runtime.gopark(0x9f6dea6b13c?, 0x1?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000423f38 sp=0xc000423f18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc000423fc8 sp=0xc000423f38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000423fe0 sp=0xc000423fc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000423fe8 sp=0xc000423fe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 28 gp=0xc000209500 m=nil [GC worker (idle)]: runtime.gopark(0x9f6dea6b13c?, 0x1?, 0x8?, 0x9?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00042df38 sp=0xc00042df18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc00042dfc8 sp=0xc00042df38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00042dfe0 sp=0xc00042dfc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00042dfe8 sp=0xc00042dfe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 29 gp=0xc0002096c0 m=nil [GC worker (idle)]: runtime.gopark(0x9f6dea6b13c?, 0x1?, 0x24?, 0xb1?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00042ff38 sp=0xc00042ff18 pc=0x7ff78e6b03ee runtime.gcBgMarkWorker(0xc0002df1f0) runtime/mgc.go:1412 +0xe9 fp=0xc00042ffc8 sp=0xc00042ff38 pc=0x7ff78e65d9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00042ffe0 sp=0xc00042ffc8 pc=0x7ff78e65d8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00042ffe8 sp=0xc00042ffe0 pc=0x7ff78e6b8921 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 34 gp=0xc00043e540 m=0 mp=0x7ff79010b1e0 [syscall]: runtime.notetsleepg(0x7ff790155ce0, 0xffffffffffffffff) runtime/lock_sema.go:296 +0x31 fp=0xc000429fa0 sp=0xc000429f68 pc=0x7ff78e650a51 os/signal.signal_recv() runtime/sigqueue.go:152 +0x29 fp=0xc000429fc0 sp=0xc000429fa0 pc=0x7ff78e6b1fe9 os/signal.loop() os/signal/signal_unix.go:23 +0x13 fp=0xc000429fe0 sp=0xc000429fc0 pc=0x7ff78ea15113 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000429fe8 sp=0xc000429fe0 pc=0x7ff78e6b8921 created by os/signal.Notify.func1.1 in goroutine 1 os/signal/signal.go:151 +0x1f goroutine 35 gp=0xc00043e700 m=nil [chan receive]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00042bf00 sp=0xc00042bee0 pc=0x7ff78e6b03ee runtime.chanrecv(0xc0003f6d20, 0x0, 0x1) runtime/chan.go:639 +0x41e fp=0xc00042bf78 sp=0xc00042bf00 pc=0x7ff78e64acbe runtime.chanrecv1(0x0?, 0x0?) runtime/chan.go:489 +0x12 fp=0xc00042bfa0 sp=0xc00042bf78 pc=0x7ff78e64a872 github.com/ollama/ollama/server.Serve.func2() github.com/ollama/ollama/server/routes.go:1255 +0x3d fp=0xc00042bfe0 sp=0xc00042bfa0 pc=0x7ff78f22ea3d runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00042bfe8 sp=0xc00042bfe0 pc=0x7ff78e6b8921 created by github.com/ollama/ollama/server.Serve in goroutine 1 github.com/ollama/ollama/server/routes.go:1254 +0x667 goroutine 36 gp=0xc00043e8c0 m=nil [select]: runtime.gopark(0xc0002bbf40?, 0x3?, 0x0?, 0x0?, 0xc0002bbcf2?) runtime/proc.go:424 +0xce fp=0xc0002bbb70 sp=0xc0002bbb50 pc=0x7ff78e6b03ee runtime.selectgo(0xc0002bbf40, 0xc0002bbcec, 0xc000000240?, 0x0, 0x7ff78f707421?, 0x1) runtime/select.go:335 +0x7a5 fp=0xc0002bbc98 sp=0xc0002bbb70 pc=0x7ff78e68efe5 github.com/ollama/ollama/server.(*Scheduler).processPending(0xc000200180, {0x7ff78f89ba80, 0xc0000c8a50}) github.com/ollama/ollama/server/sched.go:117 +0xcf fp=0xc0002bbfb8 sp=0xc0002bbc98 pc=0x7ff78f23274f github.com/ollama/ollama/server.(*Scheduler).Run.func1() github.com/ollama/ollama/server/sched.go:107 +0x1f fp=0xc0002bbfe0 sp=0xc0002bbfb8 pc=0x7ff78f23265f runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0002bbfe8 sp=0xc0002bbfe0 pc=0x7ff78e6b8921 created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1 github.com/ollama/ollama/server/sched.go:106 +0xb4 goroutine 37 gp=0xc00043ea80 m=nil [select]: runtime.gopark(0xc0003a5f50?, 0x3?, 0x0?, 0x0?, 0xc0003a5d52?) runtime/proc.go:424 +0xce fp=0xc0003a5bd8 sp=0xc0003a5bb8 pc=0x7ff78e6b03ee runtime.selectgo(0xc0003a5f50, 0xc0003a5d4c, 0x0?, 0x0, 0x0?, 0x1) runtime/select.go:335 +0x7a5 fp=0xc0003a5d00 sp=0xc0003a5bd8 pc=0x7ff78e68efe5 github.com/ollama/ollama/server.(*Scheduler).processCompleted(0xc000200180, {0x7ff78f89ba80, 0xc0000c8a50}) github.com/ollama/ollama/server/sched.go:316 +0xec fp=0xc0003a5fb8 sp=0xc0003a5d00 pc=0x7ff78f2339cc github.com/ollama/ollama/server.(*Scheduler).Run.func2() github.com/ollama/ollama/server/sched.go:111 +0x1f fp=0xc0003a5fe0 sp=0xc0003a5fb8 pc=0x7ff78f23261f runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0003a5fe8 sp=0xc0003a5fe0 pc=0x7ff78e6b8921 created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1 github.com/ollama/ollama/server/sched.go:110 +0x110 goroutine 40 gp=0xc000160c40 m=nil [select]: runtime.gopark(0xc0005c2f08?, 0x2?, 0x0?, 0x0?, 0xc0005c2eb4?) runtime/proc.go:424 +0xce fp=0xc0005c2cc8 sp=0xc0005c2ca8 pc=0x7ff78e6b03ee runtime.selectgo(0xc0005c2f08, 0xc0005c2eb0, 0xffffffffffffffff?, 0x0, 0x0?, 0x1) runtime/select.go:335 +0x7a5 fp=0xc0005c2df0 sp=0xc0005c2cc8 pc=0x7ff78e68efe5 github.com/ollama/ollama/server.(*Server).scheduleRunner(0xc000008870, {0x7ff78f89ba80, 0xc000491bd0}, {0xc000630f60, 0x2b}, {0xc0004995f8, 0x1, 0x1}, 0x0, 0x0) github.com/ollama/ollama/server/routes.go:103 +0x5f7 fp=0xc0005c30f0 sp=0xc0005c2df0 pc=0x7ff78f21fff7 github.com/ollama/ollama/server.(*Server).GenerateHandler(0xc000008870, 0xc000125400) github.com/ollama/ollama/server/routes.go:176 +0x9a7 fp=0xc0005c36d8 sp=0xc0005c30f0 pc=0x7ff78f220a87 github.com/ollama/ollama/server.(*Server).GenerateHandler-fm(0x9?) <autogenerated>:1 +0x26 fp=0xc0005c36f8 sp=0xc0005c36d8 pc=0x7ff78f242e06 github.com/gin-gonic/gin.(*Context).Next(0xc000125400) github.com/gin-gonic/gin@v1.10.0/context.go:185 +0x2b fp=0xc0005c3718 sp=0xc0005c36f8 pc=0x7ff78ec584ab github.com/ollama/ollama/server.(*Server).GenerateRoutes.allowedHostsMiddleware.func3(0xc000125400) github.com/ollama/ollama/server/routes.go:1110 +0x115 fp=0xc0005c3770 sp=0xc0005c3718 pc=0x7ff78f22dff5 github.com/gin-gonic/gin.(*Context).Next(...) github.com/gin-gonic/gin@v1.10.0/context.go:185 github.com/gin-gonic/gin.CustomRecoveryWithWriter.func1(0xc000125400) github.com/gin-gonic/gin@v1.10.0/recovery.go:102 +0x6f fp=0xc0005c37c0 sp=0xc0005c3770 pc=0x7ff78ec6636f github.com/gin-gonic/gin.(*Context).Next(...) github.com/gin-gonic/gin@v1.10.0/context.go:185 github.com/gin-gonic/gin.LoggerWithConfig.func1(0xc000125400) github.com/gin-gonic/gin@v1.10.0/logger.go:249 +0xe5 fp=0xc0005c3978 sp=0xc0005c37c0 pc=0x7ff78ec654a5 github.com/gin-gonic/gin.(*Context).Next(...) github.com/gin-gonic/gin@v1.10.0/context.go:185 github.com/gin-gonic/gin.(*Engine).handleHTTPRequest(0xc000612000, 0xc000125400) github.com/gin-gonic/gin@v1.10.0/gin.go:633 +0x892 fp=0xc0005c3ae0 sp=0xc0005c3978 pc=0x7ff78ec648d2 github.com/gin-gonic/gin.(*Engine).ServeHTTP(0xc000612000, {0x7ff78f899940, 0xc0000fa2a0}, 0xc0003d4500) github.com/gin-gonic/gin@v1.10.0/gin.go:589 +0x1b2 fp=0xc0005c3b18 sp=0xc0005c3ae0 pc=0x7ff78ec63e72 net/http.(*ServeMux).ServeHTTP(0x7ff78e651b85?, {0x7ff78f899940, 0xc0000fa2a0}, 0xc0003d4500) net/http/server.go:2747 +0x1ca fp=0xc0005c3b68 sp=0xc0005c3b18 pc=0x7ff78e9e92ca net/http.serverHandler.ServeHTTP({0x7ff78f8963d0?}, {0x7ff78f899940?, 0xc0000fa2a0?}, 0x6?) net/http/server.go:3210 +0x8e fp=0xc0005c3b98 sp=0xc0005c3b68 pc=0x7ff78ea0682e net/http.(*conn).serve(0xc0000f9cb0, {0x7ff78f89ba48, 0xc000516f60}) net/http/server.go:2092 +0x5d0 fp=0xc0005c3fb8 sp=0xc0005c3b98 pc=0x7ff78e9e5d70 net/http.(*Server).Serve.gowrap3() net/http/server.go:3360 +0x28 fp=0xc0005c3fe0 sp=0xc0005c3fb8 pc=0x7ff78e9eb1c8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0005c3fe8 sp=0xc0005c3fe0 pc=0x7ff78e6b8921 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3360 +0x485 goroutine 30 gp=0xc00043ec40 m=nil [IO wait]: runtime.gopark(0x0?, 0xc000524f20?, 0xc8?, 0x4f?, 0xc000524fcc?) runtime/proc.go:424 +0xce fp=0xc00039fd20 sp=0xc00039fd00 pc=0x7ff78e6b03ee runtime.netpollblock(0x4e4?, 0x8e648386?, 0xf7?) runtime/netpoll.go:575 +0xf7 fp=0xc00039fd58 sp=0xc00039fd20 pc=0x7ff78e674fb7 internal/poll.runtime_pollWait(0x2ba670fd9f8, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc00039fd78 sp=0xc00039fd58 pc=0x7ff78e6af665 internal/poll.(*pollDesc).wait(0xc00039fdd8?, 0x7ff78e656085?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00039fda0 sp=0xc00039fd78 pc=0x7ff78e744f07 internal/poll.execIO(0xc000524f20, 0x7ff78f75d248) internal/poll/fd_windows.go:177 +0x105 fp=0xc00039fe18 sp=0xc00039fda0 pc=0x7ff78e746345 internal/poll.(*FD).Read(0xc000524f08, {0xc000517061, 0x1, 0x1}) internal/poll/fd_windows.go:438 +0x2a7 fp=0xc00039fec0 sp=0xc00039fe18 pc=0x7ff78e747047 net.(*netFD).Read(0xc000524f08, {0xc000517061?, 0xc00039ff48?, 0x7ff78e6b1d30?}) net/fd_posix.go:55 +0x25 fp=0xc00039ff08 sp=0xc00039fec0 pc=0x7ff78e7b04e5 net.(*conn).Read(0xc000072898, {0xc000517061?, 0x0?, 0x7ff790155020?}) net/net.go:189 +0x45 fp=0xc00039ff50 sp=0xc00039ff08 pc=0x7ff78e7bfac5 net.(*TCPConn).Read(0x7ff7900bbce0?, {0xc000517061?, 0x80?, 0x0?}) <autogenerated>:1 +0x25 fp=0xc00039ff80 sp=0xc00039ff50 pc=0x7ff78e7d14e5 net/http.(*connReader).backgroundRead(0xc000517050) net/http/server.go:690 +0x37 fp=0xc00039ffc8 sp=0xc00039ff80 pc=0x7ff78e9e06f7 net/http.(*connReader).startBackgroundRead.gowrap2() net/http/server.go:686 +0x25 fp=0xc00039ffe0 sp=0xc00039ffc8 pc=0x7ff78e9e0625 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00039ffe8 sp=0xc00039ffe0 pc=0x7ff78e6b8921 created by net/http.(*connReader).startBackgroundRead in goroutine 40 net/http/server.go:686 +0xb6 goroutine 11 gp=0xc000161880 m=nil [sleep]: runtime.gopark(0x9f6ee0fd6a8?, 0x1?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000045d00 sp=0xc000045ce0 pc=0x7ff78e6b03ee time.Sleep(0xee6b280) runtime/time.go:300 +0xf7 fp=0xc000045d38 sp=0xc000045d00 pc=0x7ff78e6b4777 github.com/ollama/ollama/llm.(*llmServer).WaitUntilRunning(0xc0001f5800, {0x7ff78f89ba80, 0xc000491bd0}) github.com/ollama/ollama/llm/server.go:607 +0x10a fp=0xc000045ee0 sp=0xc000045d38 pc=0x7ff78ec9826a github.com/ollama/ollama/server.(*Scheduler).load.func1() github.com/ollama/ollama/server/sched.go:454 +0x95 fp=0xc000045fe0 sp=0xc000045ee0 pc=0x7ff78f235535 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000045fe8 sp=0xc000045fe0 pc=0x7ff78e6b8921 created by github.com/ollama/ollama/server.(*Scheduler).load in goroutine 36 github.com/ollama/ollama/server/sched.go:452 +0x7df rax 0x700000000 rbx 0x1 rcx 0x7fff4db504c4 rdx 0x0 rdi 0x7ff79005cf80 rsi 0xc8000006 rbp 0x0 rsp 0xfa0bfff340 r8 0xfa0bfff2f8 r9 0x0 r10 0x0 r11 0x246 r12 0xc00020e020 r13 0x0 r14 0x7ff7901078b0 r15 0x3ffffe2000d1fdf rip 0x7fff40a1105e rflags 0x10246 cs 0x33 fs 0x53 gs 0x2b ``` ### OS Windows ### GPU _No response_ ### CPU AMD ### Ollama version 0.5.7

GiteaMirror added the bug label 2026-04-12 17:57:48 -05:00

GiteaMirror closed this issue

2026-04-12 17:57:48 -05:00

GiteaMirror commented

2026-04-12 17:57:49 -05:00

@liangkx19 commented on GitHub (Mar 18, 2025):

@YonTracks
Because when i don‘t set CUDA_VISIBLE_DEVICES=-1, it error
so i set

when i set num_gpu=0, it also error

Other computer Intel Core i7-10510U , set CUDA_VISIBLE_DEVICES=-1 can run normally, bu not set error

@liangkx19 commented on GitHub (Mar 18, 2025): @YonTracks Because when i don‘t set `CUDA_VISIBLE_DEVICES=-1`, it error so i set when i set num_gpu=0, it also error Other computer `Intel Core i7-10510U` , set `CUDA_VISIBLE_DEVICES=-1` can run normally, bu not set error

GiteaMirror commented

2026-04-12 17:57:50 -05:00

@liangkx19 commented on GitHub (Mar 18, 2025):

I want to force the CPU to run, how to config

@liangkx19 commented on GitHub (Mar 18, 2025): I want to force the CPU to run, how to config

GiteaMirror commented

2026-04-12 17:57:51 -05:00

@liangkx19 commented on GitHub (Mar 19, 2025):

I want to force the CPU to run, how to config

there is an issue at the moment, with CUDA_VISIBLE_DEVICES=-1

does it error, with no gpu env? and no num_gpu ? it should use the cpu automatically, if no gpu. without errors. the num_gpu is an options param for the api, there is no global cpu only flag / env working with (seems to be non-functional in 0.6.*) #9836 but maybe try the num_gpu = 0

can even make create a model using cpu only with num_gpu. https://github.com/ollama/ollama/blob/main/docs/api.md#generate-request-with-options

good luck

Thanks you so much

I set CUDA_VISIBLE_DEVICES=-1 and num_gpu=0, request /api/chat success

@liangkx19 commented on GitHub (Mar 19, 2025): > > I want to force the CPU to run, how to config > > there is an issue at the moment, with `CUDA_VISIBLE_DEVICES=-1` > > does it error, with no gpu env? and no `num_gpu` ? it should use the cpu automatically, if no gpu. without errors. the num_gpu is an options param for the api, there is no global cpu only flag / env working with (seems to be non-functional in 0.6.*) [#9836](https://github.com/ollama/ollama/issues/9836) but maybe try the num_gpu = 0 > > can even make create a model using cpu only with num_gpu. https://github.com/ollama/ollama/blob/main/docs/api.md#generate-request-with-options > > good luck Thanks you so much I set `CUDA_VISIBLE_DEVICES=-1` and `num_gpu=0`, request `/api/chat ` success

GiteaMirror commented

2026-04-12 17:57:53 -05:00

@liangkx19 commented on GitHub (Mar 19, 2025):

set env: CUDA_VISIBLE_DEVICES=-1
curl http://localhost:11434/api/chat -d '{ "model": "deepseek-r1:1.5b", "messages": [ { "role": "user", "content": "why is the sky blue?" } ], "options": { "num_gpu": 0 } }'

@liangkx19 commented on GitHub (Mar 19, 2025): set env: `CUDA_VISIBLE_DEVICES=-1` ` curl http://localhost:11434/api/chat -d '{ "model": "deepseek-r1:1.5b", "messages": [ { "role": "user", "content": "why is the sky blue?" } ], "options": { "num_gpu": 0 } }' `

GiteaMirror referenced this issue

2026-04-22 09:01:50 -05:00

[GH-ISSUE #6412] for glm4-9b #29789

GiteaMirror referenced this issue

2026-04-28 16:17:17 -05:00

[GH-ISSUE #6412] for glm4-9b #50540

GiteaMirror referenced this issue

2026-05-03 23:50:38 -05:00

[GH-ISSUE #6412] for glm4-9b #66066

Sign in to join this conversation.

Branches Tags

main

hoyyeva/opencode-image-modality

hoyyeva/anthropic-renderer-local-image-path

hoyyeva/anthropic-local-image-path

dhiltgen/ci

dhiltgen/llama-runner

parth-launch-codex-app

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#6412