github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 05:31:43 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #2954] server fails to init GPU when accessing a model (GPU was detected during startup) #79493

New Issue
Closed
opened 2026-05-09 05:36:23 -05:00 by GiteaMirror · 10 comments
GiteaMirror commented 2026-05-09 05:36:23 -05:00
Owner
Copy Link

Originally created by @stephen2001 on GitHub (Mar 6, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2954

Originally assigned to: @dhiltgen on GitHub.

I am running ollama "serve" in a docker container, this is my current dockerfile

FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04

WORKDIR /opt/ollama

RUN apt-get update \
    && apt-get install -y --no-install-recommends \
        wget curl \
    && apt-get autoremove -y \
    && apt-get clean \
    && rm -rf /var/lib/{apt,dpkg,cache,log}/

# Download and install Ollama
RUN curl -L https://ollama.com/download/ollama-linux-amd64 -o /usr/bin/ollama && \
    chmod +x /usr/bin/ollama

ENV OLLAMA_DEBUG=1
ENV OLLAMA_HOST 0.0.0.0

EXPOSE 11434

# Set the entrypoint
ENTRYPOINT [ "/usr/bin/ollama" ]

# Default command
CMD ["serve"]

GPU is detected as expected

time=2024-03-06T14:07:32.512+01:00 level=INFO source=images.go:710 msg="total blobs: 6"
2024-03-06T13:07:32.514600912Z time=2024-03-06T14:07:32.514+01:00 level=INFO source=images.go:717 msg="total unused blobs removed: 0"
2024-03-06T13:07:32.516025518Z time=2024-03-06T14:07:32.515+01:00 level=INFO source=routes.go:1021 msg="Listening on [::]:11434 (version 0.1.28)"
2024-03-06T13:07:32.516175124Z time=2024-03-06T14:07:32.516+01:00 level=INFO source=payload_common.go:107 msg="Extracting dynamic libraries..."
2024-03-06T13:07:37.612422723Z time=2024-03-06T14:07:37.611+01:00 level=INFO source=payload_common.go:146 msg="Dynamic LLM libraries [cpu_avx2 cpu_avx cpu cuda_v11 rocm_v6 rocm_v5]"
2024-03-06T13:07:37.612486963Z time=2024-03-06T14:07:37.612+01:00 level=DEBUG source=payload_common.go:147 msg="Override detection logic by setting OLLAMA_LLM_LIBRARY"
2024-03-06T13:07:37.612499836Z time=2024-03-06T14:07:37.612+01:00 level=INFO source=gpu.go:94 msg="Detecting GPU type"
2024-03-06T13:07:37.612510087Z time=2024-03-06T14:07:37.612+01:00 level=INFO source=gpu.go:265 msg="Searching for GPU management library libnvidia-ml.so"
2024-03-06T13:07:37.612522996Z time=2024-03-06T14:07:37.612+01:00 level=DEBUG source=gpu.go:283 msg="gpu management search paths: [/usr/local/cuda/lib64/libnvidia-ml.so* /usr/lib/x86_64-linux-gnu/nvidia/current/libnvidia-ml.so* /usr/lib/x86_64-linux-gnu/libnvidia-ml.so* /usr/lib/wsl/lib/libnvidia-ml.so* /usr/lib/wsl/drivers/*/libnvidia-ml.so* /opt/cuda/lib64/libnvidia-ml.so* /usr/lib*/libnvidia-ml.so* /usr/local/lib*/libnvidia-ml.so* /usr/lib/aarch64-linux-gnu/nvidia/current/libnvidia-ml.so* /usr/lib/aarch64-linux-gnu/libnvidia-ml.so* /opt/cuda/targets/x86_64-linux/lib/stubs/libnvidia-ml.so* /usr/local/nvidia/lib/libnvidia-ml.so* /usr/local/nvidia/lib64/libnvidia-ml.so*]"
2024-03-06T13:07:37.614431607Z time=2024-03-06T14:07:37.614+01:00 level=INFO source=gpu.go:311 msg="Discovered GPU libraries: [/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.525.116.04]"
2024-03-06T13:07:37.614536353Z wiring nvidia management library functions in /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.525.116.04
2024-03-06T13:07:37.614565012Z dlsym: nvmlInit_v2
2024-03-06T13:07:37.614573240Z dlsym: nvmlShutdown
2024-03-06T13:07:37.614580264Z dlsym: nvmlDeviceGetHandleByIndex
2024-03-06T13:07:37.614587226Z dlsym: nvmlDeviceGetMemoryInfo
2024-03-06T13:07:37.614593900Z dlsym: nvmlDeviceGetCount_v2
2024-03-06T13:07:37.614600540Z dlsym: nvmlDeviceGetCudaComputeCapability
2024-03-06T13:07:37.614607160Z dlsym: nvmlSystemGetDriverVersion
2024-03-06T13:07:37.614613946Z dlsym: nvmlDeviceGetName
2024-03-06T13:07:37.614620480Z dlsym: nvmlDeviceGetSerial
2024-03-06T13:07:37.614627222Z dlsym: nvmlDeviceGetVbiosVersion
2024-03-06T13:07:37.614651044Z dlsym: nvmlDeviceGetBoardPartNumber
2024-03-06T13:07:37.614658210Z dlsym: nvmlDeviceGetBrand
2024-03-06T13:07:37.626543025Z CUDA driver version: 525.116.04
2024-03-06T13:07:37.626591950Z time=2024-03-06T14:07:37.626+01:00 level=INFO source=gpu.go:99 msg="Nvidia GPU detected"
2024-03-06T13:07:37.626604324Z time=2024-03-06T14:07:37.626+01:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
2024-03-06T13:07:37.632326226Z [0] CUDA device name: NVIDIA GeForce GTX 1080 Ti
2024-03-06T13:07:37.632367566Z [0] CUDA part number: 
2024-03-06T13:07:37.632380051Z nvmlDeviceGetSerial failed: 3
2024-03-06T13:07:37.632389911Z [0] CUDA vbios version: 86.02.39.00.22
2024-03-06T13:07:37.632399445Z [0] CUDA brand: 5
2024-03-06T13:07:37.632408716Z [0] CUDA totalMem 11811160064
2024-03-06T13:07:37.632418781Z [0] CUDA usedMem 96272384
2024-03-06T13:07:37.632428941Z time=2024-03-06T14:07:37.632+01:00 level=INFO source=gpu.go:146 msg="CUDA Compute Capability detected: 6.1"
2024-03-06T13:07:37.632439074Z time=2024-03-06T14:07:37.632+01:00 level=DEBUG source=gpu.go:254 msg="**cuda detected 1 devices with 10054M available memory**"
2024-03-06T13:07:45.128463945Z

After pulling a model and accessing the server via API - port 11434 (via AnythingLLM), I get follwing error message, it is not able to initialize GPU and continues with CPU.

time=2024-03-06T14:12:15.108+01:00 level=DEBUG source=payload_common.go:93 msg="ordered list of LLM libraries to try [/tmp/ollama3053854002/cuda_v11/libext_server.so /tmp/ollama3053854002/cpu_avx2/libext_server.so]"
2024-03-06T13:12:15.108672805Z loading library /tmp/ollama3053854002/cuda_v11/libext_server.so
2024-03-06T13:12:15.124892811Z time=2024-03-06T14:12:15.124+01:00 level=INFO source=dyn_ext_server.go:90 msg="Loading Dynamic llm server: /tmp/ollama3053854002/cuda_v11/libext_server.so"
2024-03-06T13:12:15.124934506Z time=2024-03-06T14:12:15.124+01:00 level=INFO source=dyn_ext_server.go:150 msg="Initializing llama server"
2024-03-06T13:12:15.126816285Z [1709730735] system info: AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | 
2024-03-06T13:12:15.126842734Z [1709730735] Performing pre-initialization of GPU
2024-03-06T13:12:15.152439571Z time=2024-03-06T14:12:15.152+01:00 level=DEBUG source=dyn_ext_server.go:157 msg="**failure during initialization: Unable to init GPU: no CUDA-capable device is detected**"
2024-03-06T13:12:15.152469986Z time=2024-03-06T14:12:15.152+01:00 level=WARN source=llm.go:162 msg="Failed to load dynamic library /tmp/ollama3053854002/cuda_v11/libext_server.so  Unable to init GPU: no CUDA-capable device is detected"
2024-03-06T13:12:15.152476725Z loading library /tmp/ollama3053854002/cpu_avx2/libext_server.so
2024-03-06T13:12:15.154618107Z

Any suggestion welcome. Thanks in advance

Originally created by @stephen2001 on GitHub (Mar 6, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2954 Originally assigned to: @dhiltgen on GitHub. I am running ollama "serve" in a docker container, this is my current dockerfile ``` FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04 WORKDIR /opt/ollama RUN apt-get update \ && apt-get install -y --no-install-recommends \ wget curl \ && apt-get autoremove -y \ && apt-get clean \ && rm -rf /var/lib/{apt,dpkg,cache,log}/ # Download and install Ollama RUN curl -L https://ollama.com/download/ollama-linux-amd64 -o /usr/bin/ollama && \ chmod +x /usr/bin/ollama ENV OLLAMA_DEBUG=1 ENV OLLAMA_HOST 0.0.0.0 EXPOSE 11434 # Set the entrypoint ENTRYPOINT [ "/usr/bin/ollama" ] # Default command CMD ["serve"] ``` GPU is detected as expected ``` time=2024-03-06T14:07:32.512+01:00 level=INFO source=images.go:710 msg="total blobs: 6" 2024-03-06T13:07:32.514600912Z time=2024-03-06T14:07:32.514+01:00 level=INFO source=images.go:717 msg="total unused blobs removed: 0" 2024-03-06T13:07:32.516025518Z time=2024-03-06T14:07:32.515+01:00 level=INFO source=routes.go:1021 msg="Listening on [::]:11434 (version 0.1.28)" 2024-03-06T13:07:32.516175124Z time=2024-03-06T14:07:32.516+01:00 level=INFO source=payload_common.go:107 msg="Extracting dynamic libraries..." 2024-03-06T13:07:37.612422723Z time=2024-03-06T14:07:37.611+01:00 level=INFO source=payload_common.go:146 msg="Dynamic LLM libraries [cpu_avx2 cpu_avx cpu cuda_v11 rocm_v6 rocm_v5]" 2024-03-06T13:07:37.612486963Z time=2024-03-06T14:07:37.612+01:00 level=DEBUG source=payload_common.go:147 msg="Override detection logic by setting OLLAMA_LLM_LIBRARY" 2024-03-06T13:07:37.612499836Z time=2024-03-06T14:07:37.612+01:00 level=INFO source=gpu.go:94 msg="Detecting GPU type" 2024-03-06T13:07:37.612510087Z time=2024-03-06T14:07:37.612+01:00 level=INFO source=gpu.go:265 msg="Searching for GPU management library libnvidia-ml.so" 2024-03-06T13:07:37.612522996Z time=2024-03-06T14:07:37.612+01:00 level=DEBUG source=gpu.go:283 msg="gpu management search paths: [/usr/local/cuda/lib64/libnvidia-ml.so* /usr/lib/x86_64-linux-gnu/nvidia/current/libnvidia-ml.so* /usr/lib/x86_64-linux-gnu/libnvidia-ml.so* /usr/lib/wsl/lib/libnvidia-ml.so* /usr/lib/wsl/drivers/*/libnvidia-ml.so* /opt/cuda/lib64/libnvidia-ml.so* /usr/lib*/libnvidia-ml.so* /usr/local/lib*/libnvidia-ml.so* /usr/lib/aarch64-linux-gnu/nvidia/current/libnvidia-ml.so* /usr/lib/aarch64-linux-gnu/libnvidia-ml.so* /opt/cuda/targets/x86_64-linux/lib/stubs/libnvidia-ml.so* /usr/local/nvidia/lib/libnvidia-ml.so* /usr/local/nvidia/lib64/libnvidia-ml.so*]" 2024-03-06T13:07:37.614431607Z time=2024-03-06T14:07:37.614+01:00 level=INFO source=gpu.go:311 msg="Discovered GPU libraries: [/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.525.116.04]" 2024-03-06T13:07:37.614536353Z wiring nvidia management library functions in /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.525.116.04 2024-03-06T13:07:37.614565012Z dlsym: nvmlInit_v2 2024-03-06T13:07:37.614573240Z dlsym: nvmlShutdown 2024-03-06T13:07:37.614580264Z dlsym: nvmlDeviceGetHandleByIndex 2024-03-06T13:07:37.614587226Z dlsym: nvmlDeviceGetMemoryInfo 2024-03-06T13:07:37.614593900Z dlsym: nvmlDeviceGetCount_v2 2024-03-06T13:07:37.614600540Z dlsym: nvmlDeviceGetCudaComputeCapability 2024-03-06T13:07:37.614607160Z dlsym: nvmlSystemGetDriverVersion 2024-03-06T13:07:37.614613946Z dlsym: nvmlDeviceGetName 2024-03-06T13:07:37.614620480Z dlsym: nvmlDeviceGetSerial 2024-03-06T13:07:37.614627222Z dlsym: nvmlDeviceGetVbiosVersion 2024-03-06T13:07:37.614651044Z dlsym: nvmlDeviceGetBoardPartNumber 2024-03-06T13:07:37.614658210Z dlsym: nvmlDeviceGetBrand 2024-03-06T13:07:37.626543025Z CUDA driver version: 525.116.04 2024-03-06T13:07:37.626591950Z time=2024-03-06T14:07:37.626+01:00 level=INFO source=gpu.go:99 msg="Nvidia GPU detected" 2024-03-06T13:07:37.626604324Z time=2024-03-06T14:07:37.626+01:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2" 2024-03-06T13:07:37.632326226Z [0] CUDA device name: NVIDIA GeForce GTX 1080 Ti 2024-03-06T13:07:37.632367566Z [0] CUDA part number: 2024-03-06T13:07:37.632380051Z nvmlDeviceGetSerial failed: 3 2024-03-06T13:07:37.632389911Z [0] CUDA vbios version: 86.02.39.00.22 2024-03-06T13:07:37.632399445Z [0] CUDA brand: 5 2024-03-06T13:07:37.632408716Z [0] CUDA totalMem 11811160064 2024-03-06T13:07:37.632418781Z [0] CUDA usedMem 96272384 2024-03-06T13:07:37.632428941Z time=2024-03-06T14:07:37.632+01:00 level=INFO source=gpu.go:146 msg="CUDA Compute Capability detected: 6.1" 2024-03-06T13:07:37.632439074Z time=2024-03-06T14:07:37.632+01:00 level=DEBUG source=gpu.go:254 msg="**cuda detected 1 devices with 10054M available memory**" 2024-03-06T13:07:45.128463945Z ``` After pulling a model and accessing the server via API - port 11434 (via AnythingLLM), I get follwing error message, it is not able to initialize GPU and continues with CPU. ``` time=2024-03-06T14:12:15.108+01:00 level=DEBUG source=payload_common.go:93 msg="ordered list of LLM libraries to try [/tmp/ollama3053854002/cuda_v11/libext_server.so /tmp/ollama3053854002/cpu_avx2/libext_server.so]" 2024-03-06T13:12:15.108672805Z loading library /tmp/ollama3053854002/cuda_v11/libext_server.so 2024-03-06T13:12:15.124892811Z time=2024-03-06T14:12:15.124+01:00 level=INFO source=dyn_ext_server.go:90 msg="Loading Dynamic llm server: /tmp/ollama3053854002/cuda_v11/libext_server.so" 2024-03-06T13:12:15.124934506Z time=2024-03-06T14:12:15.124+01:00 level=INFO source=dyn_ext_server.go:150 msg="Initializing llama server" 2024-03-06T13:12:15.126816285Z [1709730735] system info: AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | 2024-03-06T13:12:15.126842734Z [1709730735] Performing pre-initialization of GPU 2024-03-06T13:12:15.152439571Z time=2024-03-06T14:12:15.152+01:00 level=DEBUG source=dyn_ext_server.go:157 msg="**failure during initialization: Unable to init GPU: no CUDA-capable device is detected**" 2024-03-06T13:12:15.152469986Z time=2024-03-06T14:12:15.152+01:00 level=WARN source=llm.go:162 msg="Failed to load dynamic library /tmp/ollama3053854002/cuda_v11/libext_server.so Unable to init GPU: no CUDA-capable device is detected" 2024-03-06T13:12:15.152476725Z loading library /tmp/ollama3053854002/cpu_avx2/libext_server.so 2024-03-06T13:12:15.154618107Z ``` Any suggestion welcome. Thanks in advance
GiteaMirror commented 2026-05-09 05:36:24 -05:00
Author
Owner
Copy Link

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

Were you unable to get our official container image to work?

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

<!-- gh-comment-id:1981247314 --> @dhiltgen commented on GitHub (Mar 6, 2024): Were you unable to get our official container image to work? https://hub.docker.com/r/ollama/ollama
GiteaMirror commented 2026-05-09 05:36:25 -05:00
Author
Owner
Copy Link

@stephen2001 commented on GitHub (Mar 6, 2024):

Yes, I tried the official image, it has the same problem, but was more difficult for me to setup. I needed to install cuda inside of container. Your docker image works well directly on a machine, but as a container it has some issues. The dockerfile above I copied from another issue resolution.

<!-- gh-comment-id:1981413259 --> @stephen2001 commented on GitHub (Mar 6, 2024): Yes, I tried the official image, it has the same problem, but was more difficult for me to setup. I needed to install cuda inside of container. Your docker image works well directly on a machine, but as a container it has some issues. The dockerfile above I copied from another issue resolution.
GiteaMirror commented 2026-05-09 05:36:25 -05:00
Author
Owner
Copy Link

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

We build with CUDA v11.3.1 to maximize compatibility, so maybe switching your base layer would help?

If you exec into the container, does nvidia-smi report the GPU?

What host OS are you running? What container runtime?

<!-- gh-comment-id:1981863549 --> @dhiltgen commented on GitHub (Mar 6, 2024): We build with CUDA v11.3.1 to maximize compatibility, so maybe switching your base layer would help? If you exec into the container, does `nvidia-smi` report the GPU? What host OS are you running? What container runtime?
GiteaMirror commented 2026-05-09 05:36:26 -05:00
Author
Owner
Copy Link

@stephen2001 commented on GitHub (Mar 7, 2024):

I will try with 11.3.
This is what SMI reports
image
host os: Ubuntu 22.04.3 LTS
docker version 24.0.5, build ced0996
cannot change the server too much, since it is a gpu server that I share with others

<!-- gh-comment-id:1982880331 --> @stephen2001 commented on GitHub (Mar 7, 2024): I will try with 11.3. This is what SMI reports ![image](https://github.com/ollama/ollama/assets/23563824/4c8dc4f8-3897-4878-b9de-6e22e3e50d69) host os: Ubuntu 22.04.3 LTS docker version 24.0.5, build ced0996 cannot change the server too much, since it is a gpu server that I share with others
GiteaMirror commented 2026-05-09 05:36:27 -05:00
Author
Owner
Copy Link

@stephen2001 commented on GitHub (Mar 7, 2024):

tried with cuda 11.3, -- no difference

<!-- gh-comment-id:1983698298 --> @stephen2001 commented on GitHub (Mar 7, 2024): tried with cuda 11.3, -- no difference
GiteaMirror commented 2026-05-09 05:36:30 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 20, 2024):

Can you capture the output from the following so we can try to get to the bottom of why it's not able to detect the GPU?

docker run --rm -it  --gpus=all -p 11434:11434 -e OLLAMA_DEBUG=1 ollama/ollama:0.1.29

Then just try to load a small model so we can see what happens during the GPU discovery.

<!-- gh-comment-id:2010017945 --> @dhiltgen commented on GitHub (Mar 20, 2024): Can you capture the output from the following so we can try to get to the bottom of why it's not able to detect the GPU? ``` docker run --rm -it --gpus=all -p 11434:11434 -e OLLAMA_DEBUG=1 ollama/ollama:0.1.29 ``` Then just try to load a small model so we can see what happens during the GPU discovery.
GiteaMirror commented 2026-05-09 05:36:32 -05:00
Author
Owner
Copy Link

@stephen2001 commented on GitHub (Mar 21, 2024):

Many thanks.
I found a way to run original docker image directly on server behind firewall. It is a bit hacky, but it looks like using GPU now. Need to get GPU device usage fixed (cannot use --gpus=all, but only dedicated device).
Will check and let you know

<!-- gh-comment-id:2012835614 --> @stephen2001 commented on GitHub (Mar 21, 2024): Many thanks. I found a way to run original docker image directly on server behind firewall. It is a bit hacky, but it looks like using GPU now. Need to get GPU device usage fixed (cannot use --gpus=all, but only dedicated device). Will check and let you know
GiteaMirror commented 2026-05-09 05:36:34 -05:00
Author
Owner
Copy Link

@vakaobr commented on GitHub (Mar 28, 2024):

Hey @stephen2001 can you please advise how to do it ? I'm facing the same issue when trying to run this as a container

<!-- gh-comment-id:2024766378 --> @vakaobr commented on GitHub (Mar 28, 2024): Hey @stephen2001 can you please advise how to do it ? I'm facing the same issue when trying to run this as a container
GiteaMirror commented 2026-05-09 05:36:35 -05:00
Author
Owner
Copy Link

@stephen2001 commented on GitHub (Apr 8, 2024):

Hi @vakaobr,
a) I have translated
docker run --rm -it --gpus=all -p 11434:11434 -e OLLAMA_DEBUG=1 ollama/ollama:0.1.29
into a run configuration in PyCharm that I am using to directly create a docker container on my machine

b) once container is running you can create a terminal (or attach to the docker container)

c) I needed to download / update certificates to get pull of models running

d) there seems to be a bug in ollama that requires to unset http_proxy and HTTP_PROXY environment variables. Of course https_proxy and HTTPS_PROXY need to be existing

e) now you can pull / run models

hope this helps

<!-- gh-comment-id:2042846771 --> @stephen2001 commented on GitHub (Apr 8, 2024): Hi @vakaobr, a) I have translated docker run --rm -it --gpus=all -p 11434:11434 -e OLLAMA_DEBUG=1 ollama/ollama:0.1.29 into a run configuration in PyCharm that I am using to directly create a docker container on my machine b) once container is running you can create a terminal (or attach to the docker container) c) I needed to download / update certificates to get pull of models running d) there seems to be a bug in ollama that requires to unset http_proxy and HTTP_PROXY environment variables. Of course https_proxy and HTTPS_PROXY need to be existing e) now you can pull / run models hope this helps
GiteaMirror commented 2026-05-09 05:36:36 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 15, 2024):

Glad to hear you got it working! Sounds like we can close this issue now.

<!-- gh-comment-id:2057928859 --> @dhiltgen commented on GitHub (Apr 15, 2024): Glad to hear you got it working! Sounds like we can close this issue now.
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
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#79493
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?