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 #3774] Error: llama runner process no longer running: 3221225785 #28089

New Issue
Closed
opened 2026-04-22 05:54:27 -05:00 by GiteaMirror · 29 comments
GiteaMirror commented 2026-04-22 05:54:27 -05:00
Owner
Copy Link

Originally created by @pheonixravi on GitHub (Apr 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3774

Originally assigned to: @dhiltgen on GitHub.

server.log

Unable to run mistral or any other modal locally using ollama

C:\Users\ravik>ollama list
NAME ID SIZE MODIFIED
mistral:latest 61e88e884507 4.1 GB About an hour ago

C:\Users\ravik>ollama run mistral
Error: llama runner process no longer running: 3221225785

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

No response

Originally created by @pheonixravi on GitHub (Apr 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3774 Originally assigned to: @dhiltgen on GitHub. [server.log](https://github.com/ollama/ollama/files/15047891/server.log) ### Unable to run mistral or any other modal locally using ollama C:\Users\ravik>ollama list NAME ID SIZE MODIFIED mistral:latest 61e88e884507 4.1 GB About an hour ago C:\Users\ravik>ollama run mistral Error: llama runner process no longer running: 3221225785 ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version _No response_
GiteaMirror added the bugwindows labels 2026-04-22 05:54:27 -05:00
GiteaMirror commented 2026-04-22 05:54:30 -05:00
Author
Owner
Copy Link

@carsonfeng commented on GitHub (Apr 21, 2024):

similar case:

ollama run llama3:70b
Error: llama runner process no longer running: 1 error:failed to create context with model '/root/.ollama/models/blobs/sha256-4fe022a8902336d3c452c88f7aca5590f5b5b02ccfd06320fdefab02412e1f0b'

<!-- gh-comment-id:2067836059 --> @carsonfeng commented on GitHub (Apr 21, 2024): similar case: ollama run llama3:70b Error: llama runner process no longer running: 1 error:failed to create context with model '/root/.ollama/models/blobs/sha256-4fe022a8902336d3c452c88f7aca5590f5b5b02ccfd06320fdefab02412e1f0b'
GiteaMirror commented 2026-04-22 05:54:30 -05:00
Author
Owner
Copy Link

@fearnworks commented on GitHub (Apr 21, 2024):

Same issue here.

<!-- gh-comment-id:2068074802 --> @fearnworks commented on GitHub (Apr 21, 2024): Same issue here.
GiteaMirror commented 2026-04-22 05:54:30 -05:00
Author
Owner
Copy Link

@diegocaumont commented on GitHub (Apr 22, 2024):

Same case here.

<!-- gh-comment-id:2068688005 --> @diegocaumont commented on GitHub (Apr 22, 2024): Same case here.
GiteaMirror commented 2026-04-22 05:54:30 -05:00
Author
Owner
Copy Link

@hunt-47 commented on GitHub (Apr 22, 2024):

same issue here

<!-- gh-comment-id:2068934965 --> @hunt-47 commented on GitHub (Apr 22, 2024): same issue here
GiteaMirror commented 2026-04-22 05:54:31 -05:00
Author
Owner
Copy Link

@ecsfu commented on GitHub (Apr 22, 2024):

same issue here

<!-- gh-comment-id:2069569037 --> @ecsfu commented on GitHub (Apr 22, 2024): same issue here
GiteaMirror commented 2026-04-22 05:54:31 -05:00
Author
Owner
Copy Link

@anishchhaparwal commented on GitHub (Apr 23, 2024):

same issue

<!-- gh-comment-id:2072668579 --> @anishchhaparwal commented on GitHub (Apr 23, 2024): same issue
GiteaMirror commented 2026-04-22 05:54:31 -05:00
Author
Owner
Copy Link

@kiririnou commented on GitHub (Apr 23, 2024):

same issue with llama3 and windows

time=2024-04-23T21:00:09.249+03:00 level=INFO source=server.go:389 msg="waiting for llama runner to start responding"
time=2024-04-23T21:00:09.305+03:00 level=ERROR source=routes.go:120 msg="error loading llama server" error="llama runner process no longer running: 3221225781 "
[GIN] 2024/04/23 - 21:00:09 | 500 |    1.6587976s |       127.0.0.1 | POST     "/api/chat"
<!-- gh-comment-id:2073064862 --> @kiririnou commented on GitHub (Apr 23, 2024): same issue with llama3 and windows ``` time=2024-04-23T21:00:09.249+03:00 level=INFO source=server.go:389 msg="waiting for llama runner to start responding" time=2024-04-23T21:00:09.305+03:00 level=ERROR source=routes.go:120 msg="error loading llama server" error="llama runner process no longer running: 3221225781 " [GIN] 2024/04/23 - 21:00:09 | 500 | 1.6587976s | 127.0.0.1 | POST "/api/chat" ```
GiteaMirror commented 2026-04-22 05:54:31 -05:00
Author
Owner
Copy Link

@hammad93 commented on GitHub (Apr 23, 2024):

Hello, I was testing this on a Rasberry Pi CM4 with the aarch64 (ARM) architecture and also received the same error. As a workaround, I was able to run it through Docker,

https://hub.docker.com/r/ollama/ollama

The commands I used include,

docker pull --platform linux/arm64 ollama/ollama 
docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
docker exec -it ollama ollama run phi

Remove the --platform flag for other setups
I appreciated that the Docker image was only ~320 MB

<!-- gh-comment-id:2073281974 --> @hammad93 commented on GitHub (Apr 23, 2024): Hello, I was testing this on a Rasberry Pi CM4 with the aarch64 (ARM) architecture and also received the same error. As a workaround, I was able to run it through Docker, https://hub.docker.com/r/ollama/ollama The commands I used include, ``` docker pull --platform linux/arm64 ollama/ollama docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama docker exec -it ollama ollama run phi ``` Remove the `--platform` flag for other setups I appreciated that the Docker image was only ~320 MB
GiteaMirror commented 2026-04-22 05:54:32 -05:00
Author
Owner
Copy Link

@HughieCN commented on GitHub (Apr 24, 2024):

Same issue here.

<!-- gh-comment-id:2074356119 --> @HughieCN commented on GitHub (Apr 24, 2024): Same issue here.
GiteaMirror commented 2026-04-22 05:54:32 -05:00
Author
Owner
Copy Link

@ironicviking commented on GitHub (Apr 24, 2024):

Same issue on windows 10, amd 7800xt. I uninstalled Ollama, downloaded 1.30, installed it as administrator and that got it working. Had to fight the updater as it tries to update directly, but i was able to get it working by installing it as administrator. So something has changed in the last release.

<!-- gh-comment-id:2074720871 --> @ironicviking commented on GitHub (Apr 24, 2024): Same issue on windows 10, amd 7800xt. I uninstalled Ollama, downloaded 1.30, installed it as administrator and that got it working. Had to fight the updater as it tries to update directly, but i was able to get it working by installing it as administrator. So something has changed in the last release.
GiteaMirror commented 2026-04-22 05:54:33 -05:00
Author
Owner
Copy Link

@hunt-47 commented on GitHub (Apr 24, 2024):

I think its the problem with the model. i encountered this issue when i tried to use a finetuned of the official version. but if you are using quantized models from TheBloke it works fine.

<!-- gh-comment-id:2075318187 --> @hunt-47 commented on GitHub (Apr 24, 2024): I think its the problem with the model. i encountered this issue when i tried to use a finetuned of the official version. but if you are using quantized models from TheBloke it works fine.
GiteaMirror commented 2026-04-22 05:54:33 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 24, 2024):

There may be a few different possible root causes, but I believe this should be resolved in 0.1.33 based on #3850

<!-- gh-comment-id:2075414696 --> @dhiltgen commented on GitHub (Apr 24, 2024): There may be a few different possible root causes, but I believe this should be resolved in 0.1.33 based on #3850
GiteaMirror commented 2026-04-22 05:54:33 -05:00
Author
Owner
Copy Link

@yhd12138 commented on GitHub (Apr 25, 2024):

There may be a few different possible root causes, but I believe this should be resolved in 0.1.33 based on #3850

Can we get the 0.1.33 version of the "ollama-windows-amd64.exe"? Thanks.

<!-- gh-comment-id:2076146975 --> @yhd12138 commented on GitHub (Apr 25, 2024): > There may be a few different possible root causes, but I believe this should be resolved in 0.1.33 based on #3850 Can we get the 0.1.33 version of the "ollama-windows-amd64.exe"? Thanks.
GiteaMirror commented 2026-04-22 05:54:34 -05:00
Author
Owner
Copy Link

@Sarolta commented on GitHub (Apr 27, 2024):

had the same issue running a undowloaded model, failed on the last step,
did a pull and it succeeded. Then the run command worked.

<!-- gh-comment-id:2080347289 --> @Sarolta commented on GitHub (Apr 27, 2024): had the same issue running a undowloaded model, failed on the last step, did a pull and it succeeded. Then the run command worked.
GiteaMirror commented 2026-04-22 05:54:35 -05:00
Author
Owner
Copy Link

@abhishekmyway commented on GitHub (Apr 28, 2024):

Still its same issue on linux:
Screenshot 2024-04-28 195741

<!-- gh-comment-id:2081453407 --> @abhishekmyway commented on GitHub (Apr 28, 2024): Still its same issue on linux: ![Screenshot 2024-04-28 195741](https://github.com/ollama/ollama/assets/51020286/70ef267b-9f14-4e36-b5d6-c53065860117)
GiteaMirror commented 2026-04-22 05:54:36 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 28, 2024):

The pre-release for 0.1.33 is available now, which should resolve these exe missing/disappearing problems on windows.

<!-- gh-comment-id:2081585340 --> @dhiltgen commented on GitHub (Apr 28, 2024): The pre-release for [0.1.33](https://github.com/ollama/ollama/releases) is available now, which should resolve these exe missing/disappearing problems on windows.
GiteaMirror commented 2026-04-22 05:54:36 -05:00
Author
Owner
Copy Link

@aaronjrod commented on GitHub (Apr 28, 2024):

Hey @dhiltgen! I've just installed the pre-release, since I was having this issue. The model now runs, but not via GPU: msg="[0] CUDA GPU is too old. Compute Capability detected: 1.0"

In the 0.1.32 version, it would detect my GPU (GeForce GTX 970): "CUDART CUDA Compute Capability detected: 5.2"

Any recommendations?

<!-- gh-comment-id:2081589282 --> @aaronjrod commented on GitHub (Apr 28, 2024): Hey @dhiltgen! I've just installed the pre-release, since I was having this issue. The model now runs, but not via GPU: msg="[0] CUDA GPU is too old. Compute Capability detected: 1.0" In the 0.1.32 version, it would detect my GPU (GeForce GTX 970): "CUDART CUDA Compute Capability detected: 5.2" Any recommendations?
GiteaMirror commented 2026-04-22 05:54:37 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 28, 2024):

@aaronjrod that's unexpected. Can you share the server log? We may need debug turned on, so quit the app, then in a powershell terminal run

$env:OLLAMA_DEBUG="1"
ollama serve
<!-- gh-comment-id:2081599036 --> @dhiltgen commented on GitHub (Apr 28, 2024): @aaronjrod that's unexpected. Can you share the server log? We may need debug turned on, so quit the app, then in a powershell terminal run ```powershell $env:OLLAMA_DEBUG="1" ollama serve ```
GiteaMirror commented 2026-04-22 05:54:38 -05:00
Author
Owner
Copy Link

@aaronjrod commented on GitHub (Apr 28, 2024):

@dhiltgen sure! For context, I am using an Intel i5-6400 CPU and GeForce GTX 970 GPU:

PS C:\Users\Aaron> $env:OLLAMA_DEBUG="1"
PS C:\Users\Aaron> ollama serve
time=2024-04-28T16:56:46.238-04:00 level=INFO source=images.go:821 msg="total blobs: 5"
time=2024-04-28T16:56:46.240-04:00 level=INFO source=images.go:828 msg="total unused blobs removed: 0"
time=2024-04-28T16:56:46.241-04:00 level=INFO source=routes.go:1074 msg="Listening on 127.0.0.1:11434 (version 0.1.33-rc5)"
time=2024-04-28T16:56:46.241-04:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\Aaron\AppData\Local\Programs\Ollama\ollama_runners\cpu
time=2024-04-28T16:56:46.241-04:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\Aaron\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx
time=2024-04-28T16:56:46.241-04:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\Aaron\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx2
time=2024-04-28T16:56:46.241-04:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\Aaron\AppData\Local\Programs\Ollama\ollama_runners\cuda_v11.3
time=2024-04-28T16:56:46.241-04:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\Aaron\AppData\Local\Programs\Ollama\ollama_runners\rocm_v5.7
time=2024-04-28T16:56:46.241-04:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu_avx cpu_avx2 cuda_v11.3 rocm_v5.7 cpu]"
time=2024-04-28T16:56:46.242-04:00 level=DEBUG source=payload.go:45 msg="Override detection logic by setting OLLAMA_LLM_LIBRARY"
time=2024-04-28T16:56:46.242-04:00 level=DEBUG source=sched.go:105 msg="starting llm scheduler"
time=2024-04-28T16:56:46.242-04:00 level=INFO source=gpu.go:96 msg="Detecting GPUs"
time=2024-04-28T16:56:46.243-04:00 level=DEBUG source=gpu.go:203 msg="Searching for GPU library" name=cudart64_*.dll
time=2024-04-28T16:56:46.243-04:00 level=DEBUG source=gpu.go:221 msg="gpu library search" globs="[C:\\Users\\Aaron\\AppData\\Local\\Programs\\Ollama\\cudart64_*.dll c:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v*\\bin\\cudart64_*.dll C:\\Python38\\Scripts\\cudart64_*.dll* C:\\Python38\\cudart64_*.dll* C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\cudart64_*.dll* C:\\Program Files (x86)\\Intel\\iCLS Client\\cudart64_*.dll* C:\\Program Files\\Intel\\iCLS Client\\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:\\Program Files (x86)\\Intel\\Intel(R) Management Engine Components\\DAL\\cudart64_*.dll* C:\\Program Files\\Intel\\Intel(R) Management Engine Components\\DAL\\cudart64_*.dll* C:\\Program Files (x86)\\Intel\\Intel(R) Management Engine Components\\IPT\\cudart64_*.dll* C:\\Program Files\\Intel\\Intel(R) Management Engine Components\\IPT\\cudart64_*.dll* C:\\Program Files\\TortoiseGit\\bin\\cudart64_*.dll* C:\\Program Files\\nodejs\\cudart64_*.dll* C:\\UnxTools\\cudart64_*.dll* C:\\WINDOWS\\System32\\OpenSSH\\cudart64_*.dll* C:\\Program Files\\dotnet\\cudart64_*.dll* C:\\Program Files\\Microsoft SQL Server\\130\\Tools\\Binn\\cudart64_*.dll* C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\cudart64_*.dll* C:\\Program Files (x86)\\Yarn\\bin\\cudart64_*.dll* C:\\ProgramData\\chocolatey\\bin\\cudart64_*.dll* c:\\k\\cudart64_*.dll* C:\\tools\\java\\jdk1.8.0_221\\bin\\cudart64_*.dll* C:\\Program Files\\Git\\cmd\\cudart64_*.dll* C:\\Program Files\\NVIDIA Corporation\\Nsight Compute 2024.1.1\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\Microsoft\\WindowsApps\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\atom\\bin\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\Programs\\Git\\cmd\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Roaming\\npm\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\Microsoft\\WindowsApps\\cudart64_*.dll* C:\\Users\\Aaron\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\Programs\\Microsoft VS Code\\bin\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\Programs\\Ollama\\cudart64_*.dll*]"
time=2024-04-28T16:56:46.262-04:00 level=DEBUG source=gpu.go:249 msg="discovered GPU libraries" paths="[C:\\Users\\Aaron\\AppData\\Local\\Programs\\Ollama\\cudart64_110.dll C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\cudart64_60.dll]"
cudaSetDevice err: 3
time=2024-04-28T16:56:46.462-04:00 level=DEBUG source=gpu.go:261 msg="Unable to load cudart" library=C:\Users\Aaron\AppData\Local\Programs\Ollama\cudart64_110.dll error="cudart init failure: 3"
CUDA driver version: 9-1
time=2024-04-28T16:56:46.469-04:00 level=INFO source=gpu.go:101 msg="detected GPUs" library="C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\cudart64_60.dll" count=1
time=2024-04-28T16:56:46.470-04:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
[GPU-00000000-0100-0000-00c0-000000000000] CUDA totalMem 0
[GPU-00000000-0100-0000-00c0-000000000000] CUDA freeMem 3540602060
[GPU-00000000-0100-0000-00c0-000000000000] Compute Capability 1.0
time=2024-04-28T16:56:46.552-04:00 level=INFO source=gpu.go:148 msg="[0] CUDA GPU is too old. Compute Capability detected: 1.0"
time=2024-04-28T16:56:46.554-04:00 level=DEBUG source=amd_windows.go:32 msg="unable to load amdhip64.dll: The specified module could not be found."
<!-- gh-comment-id:2081653926 --> @aaronjrod commented on GitHub (Apr 28, 2024): @dhiltgen sure! For context, I am using an Intel i5-6400 CPU and GeForce GTX 970 GPU: ``` PS C:\Users\Aaron> $env:OLLAMA_DEBUG="1" PS C:\Users\Aaron> ollama serve time=2024-04-28T16:56:46.238-04:00 level=INFO source=images.go:821 msg="total blobs: 5" time=2024-04-28T16:56:46.240-04:00 level=INFO source=images.go:828 msg="total unused blobs removed: 0" time=2024-04-28T16:56:46.241-04:00 level=INFO source=routes.go:1074 msg="Listening on 127.0.0.1:11434 (version 0.1.33-rc5)" time=2024-04-28T16:56:46.241-04:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\Aaron\AppData\Local\Programs\Ollama\ollama_runners\cpu time=2024-04-28T16:56:46.241-04:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\Aaron\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx time=2024-04-28T16:56:46.241-04:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\Aaron\AppData\Local\Programs\Ollama\ollama_runners\cpu_avx2 time=2024-04-28T16:56:46.241-04:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\Aaron\AppData\Local\Programs\Ollama\ollama_runners\cuda_v11.3 time=2024-04-28T16:56:46.241-04:00 level=DEBUG source=payload.go:71 msg="availableServers : found" file=C:\Users\Aaron\AppData\Local\Programs\Ollama\ollama_runners\rocm_v5.7 time=2024-04-28T16:56:46.241-04:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu_avx cpu_avx2 cuda_v11.3 rocm_v5.7 cpu]" time=2024-04-28T16:56:46.242-04:00 level=DEBUG source=payload.go:45 msg="Override detection logic by setting OLLAMA_LLM_LIBRARY" time=2024-04-28T16:56:46.242-04:00 level=DEBUG source=sched.go:105 msg="starting llm scheduler" time=2024-04-28T16:56:46.242-04:00 level=INFO source=gpu.go:96 msg="Detecting GPUs" time=2024-04-28T16:56:46.243-04:00 level=DEBUG source=gpu.go:203 msg="Searching for GPU library" name=cudart64_*.dll time=2024-04-28T16:56:46.243-04:00 level=DEBUG source=gpu.go:221 msg="gpu library search" globs="[C:\\Users\\Aaron\\AppData\\Local\\Programs\\Ollama\\cudart64_*.dll c:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v*\\bin\\cudart64_*.dll C:\\Python38\\Scripts\\cudart64_*.dll* C:\\Python38\\cudart64_*.dll* C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\cudart64_*.dll* C:\\Program Files (x86)\\Intel\\iCLS Client\\cudart64_*.dll* C:\\Program Files\\Intel\\iCLS Client\\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:\\Program Files (x86)\\Intel\\Intel(R) Management Engine Components\\DAL\\cudart64_*.dll* C:\\Program Files\\Intel\\Intel(R) Management Engine Components\\DAL\\cudart64_*.dll* C:\\Program Files (x86)\\Intel\\Intel(R) Management Engine Components\\IPT\\cudart64_*.dll* C:\\Program Files\\Intel\\Intel(R) Management Engine Components\\IPT\\cudart64_*.dll* C:\\Program Files\\TortoiseGit\\bin\\cudart64_*.dll* C:\\Program Files\\nodejs\\cudart64_*.dll* C:\\UnxTools\\cudart64_*.dll* C:\\WINDOWS\\System32\\OpenSSH\\cudart64_*.dll* C:\\Program Files\\dotnet\\cudart64_*.dll* C:\\Program Files\\Microsoft SQL Server\\130\\Tools\\Binn\\cudart64_*.dll* C:\\Program Files\\Microsoft SQL Server\\Client SDK\\ODBC\\170\\Tools\\Binn\\cudart64_*.dll* C:\\Program Files (x86)\\Yarn\\bin\\cudart64_*.dll* C:\\ProgramData\\chocolatey\\bin\\cudart64_*.dll* c:\\k\\cudart64_*.dll* C:\\tools\\java\\jdk1.8.0_221\\bin\\cudart64_*.dll* C:\\Program Files\\Git\\cmd\\cudart64_*.dll* C:\\Program Files\\NVIDIA Corporation\\Nsight Compute 2024.1.1\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\Microsoft\\WindowsApps\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\atom\\bin\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\Programs\\Git\\cmd\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Roaming\\npm\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\Microsoft\\WindowsApps\\cudart64_*.dll* C:\\Users\\Aaron\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\Programs\\Microsoft VS Code\\bin\\cudart64_*.dll* C:\\Users\\Aaron\\AppData\\Local\\Programs\\Ollama\\cudart64_*.dll*]" time=2024-04-28T16:56:46.262-04:00 level=DEBUG source=gpu.go:249 msg="discovered GPU libraries" paths="[C:\\Users\\Aaron\\AppData\\Local\\Programs\\Ollama\\cudart64_110.dll C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\cudart64_60.dll]" cudaSetDevice err: 3 time=2024-04-28T16:56:46.462-04:00 level=DEBUG source=gpu.go:261 msg="Unable to load cudart" library=C:\Users\Aaron\AppData\Local\Programs\Ollama\cudart64_110.dll error="cudart init failure: 3" CUDA driver version: 9-1 time=2024-04-28T16:56:46.469-04:00 level=INFO source=gpu.go:101 msg="detected GPUs" library="C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\cudart64_60.dll" count=1 time=2024-04-28T16:56:46.470-04:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2" [GPU-00000000-0100-0000-00c0-000000000000] CUDA totalMem 0 [GPU-00000000-0100-0000-00c0-000000000000] CUDA freeMem 3540602060 [GPU-00000000-0100-0000-00c0-000000000000] Compute Capability 1.0 time=2024-04-28T16:56:46.552-04:00 level=INFO source=gpu.go:148 msg="[0] CUDA GPU is too old. Compute Capability detected: 1.0" time=2024-04-28T16:56:46.554-04:00 level=DEBUG source=amd_windows.go:32 msg="unable to load amdhip64.dll: The specified module could not be found." ```
GiteaMirror commented 2026-04-22 05:54:38 -05:00
Author
Owner
Copy Link

@xavernsk commented on GitHub (Apr 30, 2024):

Facing with this issue on my windows laptop trying to use ollama with api (already used pre-release install):


C:\Users\Xaver>ollama serve
Error: listen tcp 127.0.0.1:11434: bind: Only one usage of each socket address (protocol/network address/port) is normally permitted.

C:\Users\Xaver>ollama serve
time=2024-04-30T10:12:12.263+07:00 level=INFO source=images.go:821 msg="total blobs: 5"
time=2024-04-30T10:12:12.303+07:00 level=INFO source=images.go:828 msg="total unused blobs removed: 0"
time=2024-04-30T10:12:12.305+07:00 level=INFO source=routes.go:1074 msg="Listening on 127.0.0.1:11434 (version 0.1.33-rc5)"
time=2024-04-30T10:12:12.306+07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11.3 rocm_v5.7]"
time=2024-04-30T10:12:12.306+07:00 level=INFO source=gpu.go:96 msg="Detecting GPUs"
time=2024-04-30T10:12:12.336+07:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-04-30T10:12:12.405+07:00 level=INFO source=amd_windows.go:39 msg="AMD Driver: 50422971"
time=2024-04-30T10:12:12.409+07:00 level=INFO source=amd_windows.go:68 msg="detected hip devices" count=3
time=2024-04-30T10:12:12.409+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=0 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack-
time=2024-04-30T10:12:12.409+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=0
time=2024-04-30T10:12:12.409+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=1 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack-
time=2024-04-30T10:12:12.410+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=1
time=2024-04-30T10:12:12.410+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=2 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack-
time=2024-04-30T10:12:12.410+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=2
time=2024-04-30T10:12:35.752+07:00 level=INFO source=gpu.go:96 msg="Detecting GPUs"
time=2024-04-30T10:12:35.793+07:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-04-30T10:12:35.856+07:00 level=INFO source=amd_windows.go:39 msg="AMD Driver: 50422971"
time=2024-04-30T10:12:35.860+07:00 level=INFO source=amd_windows.go:68 msg="detected hip devices" count=3
time=2024-04-30T10:12:35.860+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=0 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack-
time=2024-04-30T10:12:35.861+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=0
time=2024-04-30T10:12:35.861+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=1 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack-
time=2024-04-30T10:12:35.861+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=1
time=2024-04-30T10:12:35.861+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=2 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack-
time=2024-04-30T10:12:35.861+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=2
time=2024-04-30T10:12:41.419+07:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-04-30T10:12:41.454+07:00 level=INFO source=server.go:290 msg="starting llama server" cmd="C:\\Users\\Xaver\\AppData\\Local\\Programs\\Ollama\\ollama_runners\\cpu_avx2\\ollama_llama_server.exe --model C:\\Users\\Xaver\\.ollama\\models\\blobs\\sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29 --ctx-size 2048 --batch-size 512 --embedding --log-disable --mlock --parallel 1 --port 53577"
time=2024-04-30T10:12:41.556+07:00 level=INFO source=sched.go:327 msg="loaded runners" count=1
time=2024-04-30T10:12:41.557+07:00 level=INFO source=server.go:439 msg="waiting for llama runner to start responding"
{"function":"server_params_parse","level":"INFO","line":2603,"msg":"logging to file is disabled.","tid":"16228","timestamp":1714446761}
{"build":2737,"commit":"46e12c4","function":"wmain","level":"INFO","line":2820,"msg":"build info","tid":"16228","timestamp":1714446761}
{"function":"wmain","level":"INFO","line":2827,"msg":"system info","n_threads":6,"n_threads_batch":-1,"system_info":"AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 0 | LAMMAFILE = 1 | ","tid":"16228","timestamp":1714446761,"total_threads":12}
llama_model_loader: loaded meta data with 21 key-value pairs and 291 tensors from C:\Users\Xaver\.ollama\models\blobs\sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = llama
llama_model_loader: - kv   1:                               general.name str              = Meta-Llama-3-8B-Instruct
llama_model_loader: - kv   2:                          llama.block_count u32              = 32
llama_model_loader: - kv   3:                       llama.context_length u32              = 8192
llama_model_loader: - kv   4:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv   6:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv   7:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv   8:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  10:                          general.file_type u32              = 2
llama_model_loader: - kv  11:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  12:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  14:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  16:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  17:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  18:                tokenizer.ggml.eos_token_id u32              = 128001
llama_model_loader: - kv  19:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv  20:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q4_0:  225 tensors
llama_model_loader: - type q6_K:    1 tensors
llm_load_vocab: special tokens definition check successful ( 256/128256 ).
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 128256
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: n_ctx_train      = 8192
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 4
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 14336
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx  = 8192
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: model type       = 8B
llm_load_print_meta: model ftype      = Q4_0
llm_load_print_meta: model params     = 8.03 B
llm_load_print_meta: model size       = 4.33 GiB (4.64 BPW)
llm_load_print_meta: general.name     = Meta-Llama-3-8B-Instruct
llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token        = 128001 '<|end_of_text|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
llm_load_tensors: ggml ctx size =    0.15 MiB
llm_load_tensors:        CPU buffer size =  4437.80 MiB
.......................................................................................
llama_new_context_with_model: n_ctx      = 2048
llama_new_context_with_model: n_batch    = 512
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: freq_base  = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init:        CPU KV buffer size =   256.00 MiB
llama_new_context_with_model: KV self size  =  256.00 MiB, K (f16):  128.00 MiB, V (f16):  128.00 MiB
llama_new_context_with_model:        CPU  output buffer size =     0.50 MiB
ggml_backend_cpu_buffer_type_alloc_buffer: failed to allocate buffer of size 271056928
ggml_gallocr_reserve_n: failed to allocate CPU buffer of size 271056896
llama_new_context_with_model: failed to allocate compute buffers
llama_init_from_gpt_params: error: failed to create context with model 'C:\Users\Xaver\.ollama\models\blobs\sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29'
{"function":"load_model","level":"ERR","line":410,"model":"C:\\Users\\Xaver\\.ollama\\models\\blobs\\sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29","msg":"unable to load model","tid":"16228","timestamp":1714446773}
time=2024-04-30T10:12:54.007+07:00 level=ERROR source=sched.go:333 msg="error loading llama server" error="llama runner process no longer running: 1 error:failed to create context with model 'C:\\Users\\Xaver\\.ollama\\models\\blobs\\sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29'"
[GIN] 2024/04/30 - 10:12:54 | 500 |   18.2617974s |       127.0.0.1 | POST     "/api/generate"
<!-- gh-comment-id:2084297136 --> @xavernsk commented on GitHub (Apr 30, 2024): Facing with this issue on my windows laptop trying to use ollama with api (already used pre-release install): ```shell C:\Users\Xaver>ollama serve Error: listen tcp 127.0.0.1:11434: bind: Only one usage of each socket address (protocol/network address/port) is normally permitted. C:\Users\Xaver>ollama serve time=2024-04-30T10:12:12.263+07:00 level=INFO source=images.go:821 msg="total blobs: 5" time=2024-04-30T10:12:12.303+07:00 level=INFO source=images.go:828 msg="total unused blobs removed: 0" time=2024-04-30T10:12:12.305+07:00 level=INFO source=routes.go:1074 msg="Listening on 127.0.0.1:11434 (version 0.1.33-rc5)" time=2024-04-30T10:12:12.306+07:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11.3 rocm_v5.7]" time=2024-04-30T10:12:12.306+07:00 level=INFO source=gpu.go:96 msg="Detecting GPUs" time=2024-04-30T10:12:12.336+07:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2" time=2024-04-30T10:12:12.405+07:00 level=INFO source=amd_windows.go:39 msg="AMD Driver: 50422971" time=2024-04-30T10:12:12.409+07:00 level=INFO source=amd_windows.go:68 msg="detected hip devices" count=3 time=2024-04-30T10:12:12.409+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=0 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack- time=2024-04-30T10:12:12.409+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=0 time=2024-04-30T10:12:12.409+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=1 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack- time=2024-04-30T10:12:12.410+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=1 time=2024-04-30T10:12:12.410+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=2 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack- time=2024-04-30T10:12:12.410+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=2 time=2024-04-30T10:12:35.752+07:00 level=INFO source=gpu.go:96 msg="Detecting GPUs" time=2024-04-30T10:12:35.793+07:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2" time=2024-04-30T10:12:35.856+07:00 level=INFO source=amd_windows.go:39 msg="AMD Driver: 50422971" time=2024-04-30T10:12:35.860+07:00 level=INFO source=amd_windows.go:68 msg="detected hip devices" count=3 time=2024-04-30T10:12:35.860+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=0 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack- time=2024-04-30T10:12:35.861+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=0 time=2024-04-30T10:12:35.861+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=1 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack- time=2024-04-30T10:12:35.861+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=1 time=2024-04-30T10:12:35.861+07:00 level=INFO source=amd_windows.go:88 msg="hip device" id=2 name="AMD Radeon(TM) Graphics" gfx=gfx90c:xnack- time=2024-04-30T10:12:35.861+07:00 level=INFO source=amd_windows.go:99 msg="iGPU detected skipping" id=2 time=2024-04-30T10:12:41.419+07:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2" time=2024-04-30T10:12:41.454+07:00 level=INFO source=server.go:290 msg="starting llama server" cmd="C:\\Users\\Xaver\\AppData\\Local\\Programs\\Ollama\\ollama_runners\\cpu_avx2\\ollama_llama_server.exe --model C:\\Users\\Xaver\\.ollama\\models\\blobs\\sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29 --ctx-size 2048 --batch-size 512 --embedding --log-disable --mlock --parallel 1 --port 53577" time=2024-04-30T10:12:41.556+07:00 level=INFO source=sched.go:327 msg="loaded runners" count=1 time=2024-04-30T10:12:41.557+07:00 level=INFO source=server.go:439 msg="waiting for llama runner to start responding" {"function":"server_params_parse","level":"INFO","line":2603,"msg":"logging to file is disabled.","tid":"16228","timestamp":1714446761} {"build":2737,"commit":"46e12c4","function":"wmain","level":"INFO","line":2820,"msg":"build info","tid":"16228","timestamp":1714446761} {"function":"wmain","level":"INFO","line":2827,"msg":"system info","n_threads":6,"n_threads_batch":-1,"system_info":"AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 0 | LAMMAFILE = 1 | ","tid":"16228","timestamp":1714446761,"total_threads":12} llama_model_loader: loaded meta data with 21 key-value pairs and 291 tensors from C:\Users\Xaver\.ollama\models\blobs\sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.name str = Meta-Llama-3-8B-Instruct llama_model_loader: - kv 2: llama.block_count u32 = 32 llama_model_loader: - kv 3: llama.context_length u32 = 8192 llama_model_loader: - kv 4: llama.embedding_length u32 = 4096 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.attention.head_count u32 = 32 llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 8: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: general.file_type u32 = 2 llama_model_loader: - kv 11: llama.vocab_size u32 = 128256 llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 16: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 128001 llama_model_loader: - kv 19: tokenizer.chat_template str = {% set loop_messages = messages %}{% ... llama_model_loader: - kv 20: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_0: 225 tensors llama_model_loader: - type q6_K: 1 tensors llm_load_vocab: special tokens definition check successful ( 256/128256 ). llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 4 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 14336 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_yarn_orig_ctx = 8192 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: model type = 8B llm_load_print_meta: model ftype = Q4_0 llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 4.33 GiB (4.64 BPW) llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128001 '<|end_of_text|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_tensors: ggml ctx size = 0.15 MiB llm_load_tensors: CPU buffer size = 4437.80 MiB ....................................................................................... llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: freq_base = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CPU KV buffer size = 256.00 MiB llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB llama_new_context_with_model: CPU output buffer size = 0.50 MiB ggml_backend_cpu_buffer_type_alloc_buffer: failed to allocate buffer of size 271056928 ggml_gallocr_reserve_n: failed to allocate CPU buffer of size 271056896 llama_new_context_with_model: failed to allocate compute buffers llama_init_from_gpt_params: error: failed to create context with model 'C:\Users\Xaver\.ollama\models\blobs\sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29' {"function":"load_model","level":"ERR","line":410,"model":"C:\\Users\\Xaver\\.ollama\\models\\blobs\\sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29","msg":"unable to load model","tid":"16228","timestamp":1714446773} time=2024-04-30T10:12:54.007+07:00 level=ERROR source=sched.go:333 msg="error loading llama server" error="llama runner process no longer running: 1 error:failed to create context with model 'C:\\Users\\Xaver\\.ollama\\models\\blobs\\sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29'" [GIN] 2024/04/30 - 10:12:54 | 500 | 18.2617974s | 127.0.0.1 | POST "/api/generate" ```
GiteaMirror commented 2026-04-22 05:54:39 -05:00
Author
Owner
Copy Link

@abluejay-piyo commented on GitHub (May 1, 2024):

same with mixtral:8x22b

<!-- gh-comment-id:2087950831 --> @abluejay-piyo commented on GitHub (May 1, 2024): same with mixtral:8x22b
GiteaMirror commented 2026-04-22 05:54:39 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (May 1, 2024):

@aaronjrod's issue with the PhysX version of cudart is being tracked in #4008 with a workaround to adjust your PATH to point to a different CUDA directory first.

@xavernsk I could be misreading the logs, but it seems like you may be trying to load a model that's larger than your physical memory. failed to allocate CPU buffer of size 271056896

@anjia1991 can you share your server log?

<!-- gh-comment-id:2088720894 --> @dhiltgen commented on GitHub (May 1, 2024): @aaronjrod's issue with the PhysX version of cudart is being tracked in #4008 with a workaround to adjust your PATH to point to a different CUDA directory first. @xavernsk I could be misreading the logs, but it seems like you may be trying to load a model that's larger than your physical memory. `failed to allocate CPU buffer of size 271056896` @anjia1991 can you share your server log?
GiteaMirror commented 2026-04-22 05:54:40 -05:00
Author
Owner
Copy Link

@dylan-sh commented on GitHub (May 2, 2024):

same with mixtral:8x22b ubuntu 4090

<!-- gh-comment-id:2089775000 --> @dylan-sh commented on GitHub (May 2, 2024): same with mixtral:8x22b ubuntu 4090
GiteaMirror commented 2026-04-22 05:54:41 -05:00
Author
Owner
Copy Link

@kiririnou commented on GitHub (May 5, 2024):

After updating to 0.1.33 version, was able to successfully run llama3 on windows.

<!-- gh-comment-id:2094971547 --> @kiririnou commented on GitHub (May 5, 2024): After updating to 0.1.33 version, was able to successfully run llama3 on windows.
GiteaMirror commented 2026-04-22 05:54:42 -05:00
Author
Owner
Copy Link

@benlodz commented on GitHub (May 6, 2024):

I was having the same exact issue on Arch and I can confirm it's gone away for me too.

<!-- gh-comment-id:2096038319 --> @benlodz commented on GitHub (May 6, 2024): I was having the same exact issue on Arch and I can confirm it's gone away for me too.
GiteaMirror commented 2026-04-22 05:54:43 -05:00
Author
Owner
Copy Link

@pheonixravi commented on GitHub (May 7, 2024):

Yes,same for me,it's been resolved after the updates.

On Mon, May 6, 2024 at 3:49 AM kiririnou @.***> wrote:

After updating to 0.1.33 version, was able to successfully run llama3 on
windows.

—
Reply to this email directly, view it on GitHub
https://github.com/ollama/ollama/issues/3774#issuecomment-2094971547,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/ACNUDAE7MUQA43YMBNIEAUDZA2V65AVCNFSM6AAAAABGQMYECKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAOJUHE3TCNJUG4
.
You are receiving this because you authored the thread.Message ID:
@.***>

--

*K. Ravikumar *

<!-- gh-comment-id:2097489073 --> @pheonixravi commented on GitHub (May 7, 2024): Yes,same for me,it's been resolved after the updates. On Mon, May 6, 2024 at 3:49 AM kiririnou ***@***.***> wrote: > After updating to 0.1.33 version, was able to successfully run llama3 on > windows. > > — > Reply to this email directly, view it on GitHub > <https://github.com/ollama/ollama/issues/3774#issuecomment-2094971547>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/ACNUDAE7MUQA43YMBNIEAUDZA2V65AVCNFSM6AAAAABGQMYECKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAOJUHE3TCNJUG4> > . > You are receiving this because you authored the thread.Message ID: > ***@***.***> > -- *K. Ravikumar *
GiteaMirror commented 2026-04-22 05:54:43 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (May 7, 2024):

Sounds like we can close this issue out as resolved now. The PhysX bug should also be resolved in the next release (0.1.34) when it comes out.

<!-- gh-comment-id:2098776892 --> @dhiltgen commented on GitHub (May 7, 2024): Sounds like we can close this issue out as resolved now. The PhysX bug should also be resolved in the next release (0.1.34) when it comes out.
GiteaMirror commented 2026-04-22 05:54:44 -05:00
Author
Owner
Copy Link

@colorfuldarkgray commented on GitHub (Aug 4, 2024):

I was trying to make llama3.1 assist me with some academic writing. First it itred to write a little bit. Then it denied to help writing a message saying literally it couldnt help me. Then this

ValueError: Ollama call failed with status code 500. Details: {"error":"llama runner process no longer running: -1 "}

Is there a disclaimer about no assisting academic writing or something??

I am trying to stop and disable ollama but I get

Failed to stop/disable ollama.service: Unit ollama.service not loaded.

<!-- gh-comment-id:2267363154 --> @colorfuldarkgray commented on GitHub (Aug 4, 2024): I was trying to make llama3.1 assist me with some academic writing. First it itred to write a little bit. Then it denied to help writing a message saying literally it couldnt help me. Then this ValueError: Ollama call failed with status code 500. Details: {"error":"llama runner process no longer running: -1 "} Is there a disclaimer about no assisting academic writing or something?? I am trying to stop and disable ollama but I get Failed to stop/disable ollama.service: Unit ollama.service not loaded.
GiteaMirror commented 2026-04-22 05:54:44 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Aug 6, 2024):

@colorfuldarkgray your problem sounds unrelated to this issue, and no, it shouldn't crash like that. Please go ahead and submit a new issue reporting your crash, and share the server logs so we can investigate.

<!-- gh-comment-id:2271724392 --> @dhiltgen commented on GitHub (Aug 6, 2024): @colorfuldarkgray your problem sounds unrelated to this issue, and no, it shouldn't crash like that. Please go ahead and submit a new issue reporting your crash, and share the server logs so we can investigate.
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 windows
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#28089
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?