github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13032] Error: 500 Internal Server Error: do load request: Post "http://127.0.0.1:11680/load": read tcp 127.0.0.1:11685->127.0.0.1:11680: wsarecv: An existing connection was forcibly closed by the remote host. #34394

New Issue
Closed
opened 2026-04-22 17:54:53 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 17:54:53 -05:00
Owner
Copy Link

Originally created by @survivor998 on GitHub (Nov 10, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13032

What is the issue?

Error: 500 Internal Server Error: do load request: Post "http://127.0.0.1:11680/load": read tcp 127.0.0.1:11685->127.0.0.1:11680: wsarecv: An existing connection was forcibly closed by the remote host.

Relevant log output

time=2025-11-10T08:45:10.464+08:00 level=INFO source=routes.go:1525 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:262144 OLLAMA_DEBUG:INFO 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 OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-11-10T08:45:10.493+08:00 level=INFO source=images.go:522 msg="total blobs: 29"
time=2025-11-10T08:45:10.494+08:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-11-10T08:45:10.495+08:00 level=INFO source=routes.go:1578 msg="Listening on 127.0.0.1:11434 (version 0.12.10)"
time=2025-11-10T08:45:10.497+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2025-11-10T08:45:10.505+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50364"
time=2025-11-10T08:45:10.952+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50370"
time=2025-11-10T08:45:11.108+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50376"
time=2025-11-10T08:45:11.624+08:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-e7309209-2017-a73d-80f8-00c15d654357 filter_id="" library=CUDA compute=12.0 name=CUDA0 description="NVIDIA GeForce RTX 5090 Laptop GPU" libdirs=ollama,cuda_v12 driver=12.9 pci_id=0000:02:00.0 type=discrete total="23.9 GiB" available="23.5 GiB"
[GIN] 2025/11/10 - 08:46:20 | 200 |       521.1µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/11/10 - 08:46:20 | 200 |      4.8193ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/11/10 - 08:46:39 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/11/10 - 08:46:39 | 200 |     63.9752ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/11/10 - 08:46:39 | 200 |     52.7208ms |       127.0.0.1 | POST     "/api/show"
time=2025-11-10T08:46:39.265+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 23788"
time=2025-11-10T08:46:42.260+08:00 level=INFO source=runner.go:442 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout"
time=2025-11-10T08:46:42.262+08:00 level=WARN source=runner.go:334 msg="unable to refresh free memory, using old values"
time=2025-11-10T08:46:42.262+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2025-11-10T08:46:42.262+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-11-10T08:46:42.262+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=24
time=2025-11-10T08:46:42.322+08:00 level=INFO source=server.go:215 msg="enabling flash attention"
time=2025-11-10T08:46:42.323+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model D:\\Ollama\\blobs\\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 --port 23794"
time=2025-11-10T08:46:42.334+08:00 level=INFO source=server.go:653 msg="loading model" "model layers"=37 requested=-1
time=2025-11-10T08:46:42.334+08:00 level=INFO source=server.go:658 msg="system memory" total="63.5 GiB" free="50.2 GiB" free_swap="53.9 GiB"
time=2025-11-10T08:46:42.334+08:00 level=INFO source=server.go:665 msg="gpu memory" id=GPU-e7309209-2017-a73d-80f8-00c15d654357 library=CUDA available="23.0 GiB" free="23.5 GiB" minimum="457.0 MiB" overhead="0 B"
time=2025-11-10T08:46:42.368+08:00 level=INFO source=runner.go:1349 msg="starting ollama engine"
time=2025-11-10T08:46:42.374+08:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:23794"
time=2025-11-10T08:46:42.377+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:262144 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-e7309209-2017-a73d-80f8-00c15d654357 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-10T08:46:42.393+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=858 num_key_values=40
load_backend: loaded CPU backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 5090 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-e7309209-2017-a73d-80f8-00c15d654357
load_backend: loaded CUDA backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2025-11-10T08:46:42.509+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:325: GGML_ASSERT(ggml_nbytes(src0) <= INT_MAX) failed
time=2025-11-10T08:46:44.202+08:00 level=INFO source=sched.go:453 msg="Load failed" model=D:\Ollama\blobs\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 error="do load request: Post \"http://127.0.0.1:23794/load\": read tcp 127.0.0.1:23799->127.0.0.1:23794: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2025/11/10 - 08:46:44 | 500 |    5.0216666s |       127.0.0.1 | POST     "/api/generate"
time=2025-11-10T08:46:44.303+08:00 level=ERROR source=server.go:273 msg="llama runner terminated" error="exit status 0xc0000409"
[GIN] 2025/11/10 - 08:48:13 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/11/10 - 08:48:13 | 200 |     49.0193ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/11/10 - 08:48:13 | 200 |     41.4317ms |       127.0.0.1 | POST     "/api/show"
time=2025-11-10T08:48:13.252+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 11673"
time=2025-11-10T08:48:13.452+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2025-11-10T08:48:13.452+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-11-10T08:48:13.452+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=24
time=2025-11-10T08:48:13.508+08:00 level=INFO source=server.go:215 msg="enabling flash attention"
time=2025-11-10T08:48:13.509+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model D:\\Ollama\\blobs\\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 --port 11680"
time=2025-11-10T08:48:13.519+08:00 level=INFO source=server.go:653 msg="loading model" "model layers"=37 requested=-1
time=2025-11-10T08:48:13.520+08:00 level=INFO source=server.go:658 msg="system memory" total="63.5 GiB" free="48.5 GiB" free_swap="52.2 GiB"
time=2025-11-10T08:48:13.520+08:00 level=INFO source=server.go:665 msg="gpu memory" id=GPU-e7309209-2017-a73d-80f8-00c15d654357 library=CUDA available="23.0 GiB" free="23.5 GiB" minimum="457.0 MiB" overhead="0 B"
time=2025-11-10T08:48:13.553+08:00 level=INFO source=runner.go:1349 msg="starting ollama engine"
time=2025-11-10T08:48:13.560+08:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:11680"
time=2025-11-10T08:48:13.564+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:262144 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-e7309209-2017-a73d-80f8-00c15d654357 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-10T08:48:13.580+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=858 num_key_values=40
load_backend: loaded CPU backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 5090 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-e7309209-2017-a73d-80f8-00c15d654357
load_backend: loaded CUDA backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2025-11-10T08:48:13.681+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:325: GGML_ASSERT(ggml_nbytes(src0) <= INT_MAX) failed
time=2025-11-10T08:48:15.148+08:00 level=INFO source=sched.go:453 msg="Load failed" model=D:\Ollama\blobs\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 error="do load request: Post \"http://127.0.0.1:11680/load\": read tcp 127.0.0.1:11685->127.0.0.1:11680: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2025/11/10 - 08:48:15 | 500 |    1.9824605s |       127.0.0.1 | POST     "/api/generate"
time=2025-11-10T08:48:15.234+08:00 level=ERROR source=server.go:273 msg="llama runner terminated" error="exit status 0xc0000409"
[GIN] 2025/11/10 - 08:48:38 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2025/11/10 - 08:48:38 | 200 |      2.1196ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/11/10 - 08:48:38 | 404 |      1.3141ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/11/10 - 08:48:41 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2025/11/10 - 08:48:41 | 200 |      1.6152ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/11/10 - 08:48:56 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2025/11/10 - 08:48:56 | 200 |      1.7522ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/11/10 - 08:49:07 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2025/11/10 - 08:53:55 | 200 |       507.9µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/11/10 - 08:53:55 | 200 |     91.1104ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/11/10 - 08:53:55 | 200 |     58.8462ms |       127.0.0.1 | POST     "/api/show"
time=2025-11-10T08:53:55.717+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55002"
time=2025-11-10T08:53:56.031+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2025-11-10T08:53:56.031+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-11-10T08:53:56.031+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=24
time=2025-11-10T08:53:56.115+08:00 level=INFO source=server.go:215 msg="enabling flash attention"
time=2025-11-10T08:53:56.117+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model D:\\Ollama\\blobs\\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 --port 49779"
time=2025-11-10T08:53:56.132+08:00 level=INFO source=server.go:653 msg="loading model" "model layers"=37 requested=-1
time=2025-11-10T08:53:56.132+08:00 level=INFO source=server.go:658 msg="system memory" total="63.5 GiB" free="46.9 GiB" free_swap="50.6 GiB"
time=2025-11-10T08:53:56.132+08:00 level=INFO source=server.go:665 msg="gpu memory" id=GPU-e7309209-2017-a73d-80f8-00c15d654357 library=CUDA available="23.0 GiB" free="23.5 GiB" minimum="457.0 MiB" overhead="0 B"
time=2025-11-10T08:53:56.171+08:00 level=INFO source=runner.go:1349 msg="starting ollama engine"
time=2025-11-10T08:53:56.177+08:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:49779"
time=2025-11-10T08:53:56.186+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:262144 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-e7309209-2017-a73d-80f8-00c15d654357 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-10T08:53:56.202+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=858 num_key_values=40
load_backend: loaded CPU backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 5090 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-e7309209-2017-a73d-80f8-00c15d654357
load_backend: loaded CUDA backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2025-11-10T08:53:56.305+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:325: GGML_ASSERT(ggml_nbytes(src0) <= INT_MAX) failed
time=2025-11-10T08:53:57.827+08:00 level=INFO source=sched.go:453 msg="Load failed" model=D:\Ollama\blobs\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 error="do load request: Post \"http://127.0.0.1:49779/load\": read tcp 127.0.0.1:49785->127.0.0.1:49779: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2025/11/10 - 08:53:57 | 500 |     2.218512s |       127.0.0.1 | POST     "/api/generate"
time=2025-11-10T08:53:57.916+08:00 level=ERROR source=server.go:273 msg="llama runner terminated" error="exit status 0xc0000409"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.12.10

Originally created by @survivor998 on GitHub (Nov 10, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13032 ### What is the issue? Error: 500 Internal Server Error: do load request: Post "http://127.0.0.1:11680/load": read tcp 127.0.0.1:11685->127.0.0.1:11680: wsarecv: An existing connection was forcibly closed by the remote host. ### Relevant log output ```shell time=2025-11-10T08:45:10.464+08:00 level=INFO source=routes.go:1525 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:262144 OLLAMA_DEBUG:INFO 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 OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-11-10T08:45:10.493+08:00 level=INFO source=images.go:522 msg="total blobs: 29" time=2025-11-10T08:45:10.494+08:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-11-10T08:45:10.495+08:00 level=INFO source=routes.go:1578 msg="Listening on 127.0.0.1:11434 (version 0.12.10)" time=2025-11-10T08:45:10.497+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-11-10T08:45:10.505+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50364" time=2025-11-10T08:45:10.952+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50370" time=2025-11-10T08:45:11.108+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 50376" time=2025-11-10T08:45:11.624+08:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-e7309209-2017-a73d-80f8-00c15d654357 filter_id="" library=CUDA compute=12.0 name=CUDA0 description="NVIDIA GeForce RTX 5090 Laptop GPU" libdirs=ollama,cuda_v12 driver=12.9 pci_id=0000:02:00.0 type=discrete total="23.9 GiB" available="23.5 GiB" [GIN] 2025/11/10 - 08:46:20 | 200 | 521.1µs | 127.0.0.1 | HEAD "/" [GIN] 2025/11/10 - 08:46:20 | 200 | 4.8193ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/11/10 - 08:46:39 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/11/10 - 08:46:39 | 200 | 63.9752ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/11/10 - 08:46:39 | 200 | 52.7208ms | 127.0.0.1 | POST "/api/show" time=2025-11-10T08:46:39.265+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 23788" time=2025-11-10T08:46:42.260+08:00 level=INFO source=runner.go:442 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout" time=2025-11-10T08:46:42.262+08:00 level=WARN source=runner.go:334 msg="unable to refresh free memory, using old values" time=2025-11-10T08:46:42.262+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2025-11-10T08:46:42.262+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-11-10T08:46:42.262+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=24 time=2025-11-10T08:46:42.322+08:00 level=INFO source=server.go:215 msg="enabling flash attention" time=2025-11-10T08:46:42.323+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model D:\\Ollama\\blobs\\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 --port 23794" time=2025-11-10T08:46:42.334+08:00 level=INFO source=server.go:653 msg="loading model" "model layers"=37 requested=-1 time=2025-11-10T08:46:42.334+08:00 level=INFO source=server.go:658 msg="system memory" total="63.5 GiB" free="50.2 GiB" free_swap="53.9 GiB" time=2025-11-10T08:46:42.334+08:00 level=INFO source=server.go:665 msg="gpu memory" id=GPU-e7309209-2017-a73d-80f8-00c15d654357 library=CUDA available="23.0 GiB" free="23.5 GiB" minimum="457.0 MiB" overhead="0 B" time=2025-11-10T08:46:42.368+08:00 level=INFO source=runner.go:1349 msg="starting ollama engine" time=2025-11-10T08:46:42.374+08:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:23794" time=2025-11-10T08:46:42.377+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:262144 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-e7309209-2017-a73d-80f8-00c15d654357 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-10T08:46:42.393+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=858 num_key_values=40 load_backend: loaded CPU backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 5090 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-e7309209-2017-a73d-80f8-00c15d654357 load_backend: loaded CUDA backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2025-11-10T08:46:42.509+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:325: GGML_ASSERT(ggml_nbytes(src0) <= INT_MAX) failed time=2025-11-10T08:46:44.202+08:00 level=INFO source=sched.go:453 msg="Load failed" model=D:\Ollama\blobs\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 error="do load request: Post \"http://127.0.0.1:23794/load\": read tcp 127.0.0.1:23799->127.0.0.1:23794: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2025/11/10 - 08:46:44 | 500 | 5.0216666s | 127.0.0.1 | POST "/api/generate" time=2025-11-10T08:46:44.303+08:00 level=ERROR source=server.go:273 msg="llama runner terminated" error="exit status 0xc0000409" [GIN] 2025/11/10 - 08:48:13 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/11/10 - 08:48:13 | 200 | 49.0193ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/11/10 - 08:48:13 | 200 | 41.4317ms | 127.0.0.1 | POST "/api/show" time=2025-11-10T08:48:13.252+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 11673" time=2025-11-10T08:48:13.452+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2025-11-10T08:48:13.452+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-11-10T08:48:13.452+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=24 time=2025-11-10T08:48:13.508+08:00 level=INFO source=server.go:215 msg="enabling flash attention" time=2025-11-10T08:48:13.509+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model D:\\Ollama\\blobs\\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 --port 11680" time=2025-11-10T08:48:13.519+08:00 level=INFO source=server.go:653 msg="loading model" "model layers"=37 requested=-1 time=2025-11-10T08:48:13.520+08:00 level=INFO source=server.go:658 msg="system memory" total="63.5 GiB" free="48.5 GiB" free_swap="52.2 GiB" time=2025-11-10T08:48:13.520+08:00 level=INFO source=server.go:665 msg="gpu memory" id=GPU-e7309209-2017-a73d-80f8-00c15d654357 library=CUDA available="23.0 GiB" free="23.5 GiB" minimum="457.0 MiB" overhead="0 B" time=2025-11-10T08:48:13.553+08:00 level=INFO source=runner.go:1349 msg="starting ollama engine" time=2025-11-10T08:48:13.560+08:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:11680" time=2025-11-10T08:48:13.564+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:262144 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-e7309209-2017-a73d-80f8-00c15d654357 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-10T08:48:13.580+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=858 num_key_values=40 load_backend: loaded CPU backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 5090 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-e7309209-2017-a73d-80f8-00c15d654357 load_backend: loaded CUDA backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2025-11-10T08:48:13.681+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:325: GGML_ASSERT(ggml_nbytes(src0) <= INT_MAX) failed time=2025-11-10T08:48:15.148+08:00 level=INFO source=sched.go:453 msg="Load failed" model=D:\Ollama\blobs\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 error="do load request: Post \"http://127.0.0.1:11680/load\": read tcp 127.0.0.1:11685->127.0.0.1:11680: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2025/11/10 - 08:48:15 | 500 | 1.9824605s | 127.0.0.1 | POST "/api/generate" time=2025-11-10T08:48:15.234+08:00 level=ERROR source=server.go:273 msg="llama runner terminated" error="exit status 0xc0000409" [GIN] 2025/11/10 - 08:48:38 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/11/10 - 08:48:38 | 200 | 2.1196ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/11/10 - 08:48:38 | 404 | 1.3141ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/11/10 - 08:48:41 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/11/10 - 08:48:41 | 200 | 1.6152ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/11/10 - 08:48:56 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/11/10 - 08:48:56 | 200 | 1.7522ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/11/10 - 08:49:07 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/11/10 - 08:53:55 | 200 | 507.9µs | 127.0.0.1 | HEAD "/" [GIN] 2025/11/10 - 08:53:55 | 200 | 91.1104ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/11/10 - 08:53:55 | 200 | 58.8462ms | 127.0.0.1 | POST "/api/show" time=2025-11-10T08:53:55.717+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 55002" time=2025-11-10T08:53:56.031+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2025-11-10T08:53:56.031+08:00 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-11-10T08:53:56.031+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=24 efficiency=16 threads=24 time=2025-11-10T08:53:56.115+08:00 level=INFO source=server.go:215 msg="enabling flash attention" time=2025-11-10T08:53:56.117+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\savior\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model D:\\Ollama\\blobs\\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 --port 49779" time=2025-11-10T08:53:56.132+08:00 level=INFO source=server.go:653 msg="loading model" "model layers"=37 requested=-1 time=2025-11-10T08:53:56.132+08:00 level=INFO source=server.go:658 msg="system memory" total="63.5 GiB" free="46.9 GiB" free_swap="50.6 GiB" time=2025-11-10T08:53:56.132+08:00 level=INFO source=server.go:665 msg="gpu memory" id=GPU-e7309209-2017-a73d-80f8-00c15d654357 library=CUDA available="23.0 GiB" free="23.5 GiB" minimum="457.0 MiB" overhead="0 B" time=2025-11-10T08:53:56.171+08:00 level=INFO source=runner.go:1349 msg="starting ollama engine" time=2025-11-10T08:53:56.177+08:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:49779" time=2025-11-10T08:53:56.186+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:262144 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-e7309209-2017-a73d-80f8-00c15d654357 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-10T08:53:56.202+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=Q4_K_M name="" description="" num_tensors=858 num_key_values=40 load_backend: loaded CPU backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 5090 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-e7309209-2017-a73d-80f8-00c15d654357 load_backend: loaded CUDA backend from C:\Users\savior\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2025-11-10T08:53:56.305+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:325: GGML_ASSERT(ggml_nbytes(src0) <= INT_MAX) failed time=2025-11-10T08:53:57.827+08:00 level=INFO source=sched.go:453 msg="Load failed" model=D:\Ollama\blobs\sha256-ed12a4674d727a74ac4816c906094ea9d3119fbea46ca93288c3ce4ffbe38c55 error="do load request: Post \"http://127.0.0.1:49779/load\": read tcp 127.0.0.1:49785->127.0.0.1:49779: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2025/11/10 - 08:53:57 | 500 | 2.218512s | 127.0.0.1 | POST "/api/generate" time=2025-11-10T08:53:57.916+08:00 level=ERROR source=server.go:273 msg="llama runner terminated" error="exit status 0xc0000409" ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.10
GiteaMirror added the bug label 2026-04-22 17:54:53 -05:00
GiteaMirror commented 2026-04-22 17:54:54 -05:00
Author
Owner
Copy Link

@survivor998 commented on GitHub (Nov 10, 2025):

the bug only happend when i uesd qwen3-Vl models(like 8b or 30b),othor models like gpt-oss,qwen2.5VL would not happened

<!-- gh-comment-id:3509051099 --> @survivor998 commented on GitHub (Nov 10, 2025): the bug only happend when i uesd qwen3-Vl models(like 8b or 30b),othor models like gpt-oss,qwen2.5VL would not happened
GiteaMirror commented 2026-04-22 17:54:54 -05:00
Author
Owner
Copy Link

@survivor998 commented on GitHub (Nov 10, 2025):

I try download serveral times,so the the network would not be the problem

<!-- gh-comment-id:3509052268 --> @survivor998 commented on GitHub (Nov 10, 2025): I try download serveral times,so the the network would not be the problem
GiteaMirror commented 2026-04-22 17:54:55 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 10, 2025):

C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:325: GGML_ASSERT(ggml_nbytes(src0) <= INT_MAX) failed

Perhaps #12998.

<!-- gh-comment-id:3509054548 --> @rick-github commented on GitHub (Nov 10, 2025): ``` C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\cpy.cu:325: GGML_ASSERT(ggml_nbytes(src0) <= INT_MAX) failed ``` Perhaps #12998.
GiteaMirror commented 2026-04-22 17:54:55 -05:00
Author
Owner
Copy Link

@magnusbonnevier commented on GitHub (Nov 10, 2025):

Seems to be related to the context window setting of 256k for some reason, as stated in the #12998 issue.

Dial it back to 128k in the UI or cli settings and see if that works.

<!-- gh-comment-id:3510207105 --> @magnusbonnevier commented on GitHub (Nov 10, 2025): Seems to be related to the context window setting of 256k for some reason, as stated in the #12998 issue. Dial it back to 128k in the UI or cli settings and see if that works.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#34394
Delete Branch "%!s()"

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