github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8089] arch linux package missing cuda v11 runners #30930

New Issue
Closed
opened 2026-04-22 10:56:04 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-22 10:56:04 -05:00
Owner
Copy Link

Originally created by @S0AndS0 on GitHub (Dec 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8089

What is the issue?

After a recent update attempting run any previously functional models now leads to errors, ex;

ollama run codellama "Hello"
#> Error: POST predict: Post "http://127.0.0.1:41711/completion": EOF

Meta/system-data

  • Initially installed version (worked) ollama-cuda-0.3.10-1-x86_64
  • Broken on or before 0.5.1-2
  • Installation method: sudo packman -S ollama-cuda
  • Linux flavor: Arch (I use Arch BTW™)

Logs (snippet)

sudo journalctl -u ollama --no-pager | grep -C3 -i -- error | sed "s/$HOSTNAME/<HOST>/g"

Dec 13 08:41:19 <HOST> ollama[6310]: time=2024-12-13T08:41:19.590-08:00 level=INFO source=server.go:594 msg="llama runner started in 1.01 seconds"
Dec 13 08:41:19 <HOST> ollama[6310]: [GIN] 2024/12/13 - 08:41:19 | 200 |  1.129576145s |       127.0.0.1 | POST     "/api/generate"
Dec 13 08:41:23 <HOST> ollama[6310]: ggml_cuda_compute_forward: ADD failed
Dec 13 08:41:23 <HOST> ollama[6310]: CUDA error: no kernel image is available for execution on the device
Dec 13 08:41:23 <HOST> ollama[6310]:   current device: 0, in function ggml_cuda_compute_forward at llama/ggml-cuda.cu:2403
Dec 13 08:41:23 <HOST> ollama[6310]:   err
Dec 13 08:41:23 <HOST> ollama[6310]: llama/ggml-cuda.cu:132: CUDA error
Dec 13 08:41:23 <HOST> ollama[6310]: ptrace: Operation not permitted.
Dec 13 08:41:23 <HOST> ollama[6310]: No stack.
Dec 13 08:41:23 <HOST> ollama[6310]: The program is not being run.
--
Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.962-08:00 level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12_avx/ollama_llama_server runner --model /var/lib/ollama/blobs/sha256-1cecc26325a197571a1961bfacf64dc6e35e0f05faf57d3c6941a982e1eb2e1d --ctx-size 2048 --batch-size 512 --n-gpu-layers 25 --threads 4 --parallel 1 --port 40811"
Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.962-08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1
Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.962-08:00 level=INFO source=server.go:555 msg="waiting for llama runner to start responding"
Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.962-08:00 level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error"
Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.998-08:00 level=INFO source=runner.go:946 msg="starting go runner"
Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.999-08:00 level=INFO source=runner.go:947 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(gcc)" threads=4
Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.999-08:00 level=INFO source=.:0 msg="Server listening on 127.0.0.1:40811"
--
Dec 13 08:42:52 <HOST> ollama[6310]: time=2024-12-13T08:42:52.414-08:00 level=INFO source=server.go:594 msg="llama runner started in 35.45 seconds"
Dec 13 08:42:52 <HOST> ollama[6310]: [GIN] 2024/12/13 - 08:42:52 | 200 |  40.77210645s |       127.0.0.1 | POST     "/api/generate"
Dec 13 08:43:07 <HOST> ollama[6310]: ggml_cuda_compute_forward: ADD failed
Dec 13 08:43:07 <HOST> ollama[6310]: CUDA error: no kernel image is available for execution on the device
Dec 13 08:43:07 <HOST> ollama[6310]:   current device: 0, in function ggml_cuda_compute_forward at llama/ggml-cuda.cu:2403
Dec 13 08:43:07 <HOST> ollama[6310]:   err
Dec 13 08:43:07 <HOST> ollama[6310]: llama/ggml-cuda.cu:132: CUDA error
Dec 13 08:43:07 <HOST> ollama[6310]: ptrace: Operation not permitted.
Dec 13 08:43:07 <HOST> ollama[6310]: No stack.
Dec 13 08:43:07 <HOST> ollama[6310]: The program is not being run.

Questions

  • Are there any additional details needed or wanted?
  • Any advice on testing intervening versions for when breaking changes were introduced?

Attachments

ollama-cuda-error.log

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.5.1

Updates

2024-12-13 09:15 -0800

Possible answer to; Any advice on testing intervening versions for when breaking changes were introduced?

Arch pacman archives for ollama-cuda are available via;

https://archive.archlinux.org/packages/o/ollama-cuda/

Steps to test:

  1. Make a directory path for saving logs 
    mkdir -vp "${HOME}/Documents/logs/pacman/downgrade"
  2. Set some Bash variables 
    _version='0.3.9-2'
_url="https://archive.archlinux.org/packages/o/ollama-cuda/ollama-cuda-${_version}-x86_64.pkg.tar.zst"

    Note: as of 09:58 -0800 incrementally downgrading to version 0.3.9-2 finally lead to joy!

  3. Downgrade package to target _version 
    script -ac "sudo pacman -U ${_url}" "${HOME}/Documents/logs/pacman/downgrade/ollama-cuda-${_version}.script"
  4. Restart service 
    sudo systemctl restart ollama.service
  5. Test if things work now 
    ollama run codellama "Hello"
#> Error: POST predict: Post "http://127.0.0.1:37775/completion": EOF

If things no work, then update _version and _url variables and try again from that step onward.

Originally created by @S0AndS0 on GitHub (Dec 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8089 ### What is the issue? After a recent update attempting run any previously functional models now leads to errors, ex; ```bash ollama run codellama "Hello" #> Error: POST predict: Post "http://127.0.0.1:41711/completion": EOF ``` ### Meta/system-data - Initially installed version (worked) `ollama-cuda-0.3.10-1-x86_64` - Broken on or before `0.5.1-2` - Installation method: `sudo packman -S ollama-cuda` - Linux _flavor_: Arch (I use Arch BTW™) ### Logs (snippet) > `sudo journalctl -u ollama --no-pager | grep -C3 -i -- error | sed "s/$HOSTNAME/<HOST>/g"` ``` Dec 13 08:41:19 <HOST> ollama[6310]: time=2024-12-13T08:41:19.590-08:00 level=INFO source=server.go:594 msg="llama runner started in 1.01 seconds" Dec 13 08:41:19 <HOST> ollama[6310]: [GIN] 2024/12/13 - 08:41:19 | 200 | 1.129576145s | 127.0.0.1 | POST "/api/generate" Dec 13 08:41:23 <HOST> ollama[6310]: ggml_cuda_compute_forward: ADD failed Dec 13 08:41:23 <HOST> ollama[6310]: CUDA error: no kernel image is available for execution on the device Dec 13 08:41:23 <HOST> ollama[6310]: current device: 0, in function ggml_cuda_compute_forward at llama/ggml-cuda.cu:2403 Dec 13 08:41:23 <HOST> ollama[6310]: err Dec 13 08:41:23 <HOST> ollama[6310]: llama/ggml-cuda.cu:132: CUDA error Dec 13 08:41:23 <HOST> ollama[6310]: ptrace: Operation not permitted. Dec 13 08:41:23 <HOST> ollama[6310]: No stack. Dec 13 08:41:23 <HOST> ollama[6310]: The program is not being run. -- Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.962-08:00 level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12_avx/ollama_llama_server runner --model /var/lib/ollama/blobs/sha256-1cecc26325a197571a1961bfacf64dc6e35e0f05faf57d3c6941a982e1eb2e1d --ctx-size 2048 --batch-size 512 --n-gpu-layers 25 --threads 4 --parallel 1 --port 40811" Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.962-08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1 Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.962-08:00 level=INFO source=server.go:555 msg="waiting for llama runner to start responding" Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.962-08:00 level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error" Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.998-08:00 level=INFO source=runner.go:946 msg="starting go runner" Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.999-08:00 level=INFO source=runner.go:947 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(gcc)" threads=4 Dec 13 08:42:16 <HOST> ollama[6310]: time=2024-12-13T08:42:16.999-08:00 level=INFO source=.:0 msg="Server listening on 127.0.0.1:40811" -- Dec 13 08:42:52 <HOST> ollama[6310]: time=2024-12-13T08:42:52.414-08:00 level=INFO source=server.go:594 msg="llama runner started in 35.45 seconds" Dec 13 08:42:52 <HOST> ollama[6310]: [GIN] 2024/12/13 - 08:42:52 | 200 | 40.77210645s | 127.0.0.1 | POST "/api/generate" Dec 13 08:43:07 <HOST> ollama[6310]: ggml_cuda_compute_forward: ADD failed Dec 13 08:43:07 <HOST> ollama[6310]: CUDA error: no kernel image is available for execution on the device Dec 13 08:43:07 <HOST> ollama[6310]: current device: 0, in function ggml_cuda_compute_forward at llama/ggml-cuda.cu:2403 Dec 13 08:43:07 <HOST> ollama[6310]: err Dec 13 08:43:07 <HOST> ollama[6310]: llama/ggml-cuda.cu:132: CUDA error Dec 13 08:43:07 <HOST> ollama[6310]: ptrace: Operation not permitted. Dec 13 08:43:07 <HOST> ollama[6310]: No stack. Dec 13 08:43:07 <HOST> ollama[6310]: The program is not being run. ``` ### Questions - Are there any additional details needed or wanted? - Any advice on testing intervening versions for when breaking changes were introduced? ### Attachments [ollama-cuda-error.log](https://github.com/user-attachments/files/18129248/ollama-cuda-error.log) ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.1 ______ ## Updates ### 2024-12-13 09:15 -0800 Possible answer to; `Any advice on testing intervening versions for when breaking changes were introduced?` Arch `pacman` archives for `ollama-cuda` are available via; https://archive.archlinux.org/packages/o/ollama-cuda/ Steps to test: 0. Make a directory path for saving logs ```bash mkdir -vp "${HOME}/Documents/logs/pacman/downgrade" ``` 1. Set some Bash variables ```bash _version='0.3.9-2' _url="https://archive.archlinux.org/packages/o/ollama-cuda/ollama-cuda-${_version}-x86_64.pkg.tar.zst" ``` > Note: as of 09:58 -0800 incrementally downgrading to version `0.3.9-2` finally lead to joy! 2. Downgrade package to target `_version` ```bash script -ac "sudo pacman -U ${_url}" "${HOME}/Documents/logs/pacman/downgrade/ollama-cuda-${_version}.script" ``` 3. Restart service ```bash sudo systemctl restart ollama.service ``` 4. Test if things work now ``` ollama run codellama "Hello" #> Error: POST predict: Post "http://127.0.0.1:37775/completion": EOF ``` If things no work, then update `_version` and `_url` variables and try again from that step onward.
GiteaMirror added the bug label 2026-04-22 10:56:04 -05:00
GiteaMirror commented 2026-04-22 10:56:06 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 13, 2024):

Dec 13 07:35:34 <HOST> ollama[730]: time=2024-12-13T07:35:34.234-08:00 level=INFO source=routes.go:1274 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v12_avx]"
Dec 13 07:35:34 <HOST> ollama[730]: time=2024-12-13T07:35:34.906-08:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-962ca16e-d3f0-3dde-ecfd-3d968f5d2d4e library=cuda variant=v11 compute=5.0 driver=12.7 name="NVIDIA GeForce GTX 960M" total="3.9 GiB" available="3.9 GiB"

This may be a build issue. The cuda variant of your device is v11 but there's no v11 runner in your package. Looking at the ollama-cuda file list there's only a cuda_v12 runner. I suggest filing a ticket with the Arch ollama-cuda maintainers.

<!-- gh-comment-id:2541917418 --> @rick-github commented on GitHub (Dec 13, 2024): ``` Dec 13 07:35:34 <HOST> ollama[730]: time=2024-12-13T07:35:34.234-08:00 level=INFO source=routes.go:1274 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v12_avx]" Dec 13 07:35:34 <HOST> ollama[730]: time=2024-12-13T07:35:34.906-08:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-962ca16e-d3f0-3dde-ecfd-3d968f5d2d4e library=cuda variant=v11 compute=5.0 driver=12.7 name="NVIDIA GeForce GTX 960M" total="3.9 GiB" available="3.9 GiB" ``` This may be a build issue. The cuda variant of your device is v11 but there's no v11 runner in your package. Looking at the [ollama-cuda](https://archlinux.org/packages/extra/x86_64/ollama-cuda/) file list there's only a cuda_v12 runner. I suggest filing a ticket with the Arch ollama-cuda maintainers.
GiteaMirror commented 2026-04-22 10:56:06 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Dec 13, 2024):

We recently merged build related changes that should make it easier for the Arch packaging folks to adapt to the new build.

Until then, you can use the official ollama install guide: https://github.com/ollama/ollama/blob/main/docs/linux.md which will include the v11 runner and should work correctly on your system.

#7499

<!-- gh-comment-id:2541930638 --> @dhiltgen commented on GitHub (Dec 13, 2024): We recently merged build related changes that should make it easier for the Arch packaging folks to adapt to the new build. Until then, you can use the official ollama install guide: https://github.com/ollama/ollama/blob/main/docs/linux.md which will include the v11 runner and should work correctly on your system. #7499
GiteaMirror commented 2026-04-22 10:56:07 -05:00
Author
Owner
Copy Link

@S0AndS0 commented on GitHub (Dec 13, 2024):

Dec 13 07:35:34 <HOST> ollama[730]: time=2024-12-13T07:35:34.234-08:00 level=INFO source=routes.go:1274 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v12_avx]"
Dec 13 07:35:34 <HOST> ollama[730]: time=2024-12-13T07:35:34.906-08:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-962ca16e-d3f0-3dde-ecfd-3d968f5d2d4e library=cuda variant=v11 compute=5.0 driver=12.7 name="NVIDIA GeForce GTX 960M" total="3.9 GiB" available="3.9 GiB"

This may be a build issue. The cuda variant of your device is v11 but there's no v11 runner in your package. Looking at the ollama-cuda file list there's only a cuda_v12 runner. I suggest filing a ticket with the Arch ollama-cuda maintainers.

Wow, thanks for the rapid response!

Looks like the bug reports system for Arch requires getting permission, so I'll get on that next, and while waiting try find a non-broken version to downgrade to.

We recently merged build related changes that should make it easier for the Arch packaging folks to adapt to the new build.

Until then, you can use the official ollama install guide: https://github.com/ollama/ollama/blob/main/docs/linux.md which will include the v11 runner and should work correctly on your system.

#7499

Sensational! I'll give that a shot if Arch team, and/or downgrading attempts, take too long to get things functional again.

Update 2024-12-13 13:00 -0800

I've got Issue opened over at Arch! And should update here once package maintainers got a fix sorted.

Thanks y'all for the fast response and concise directions!

<!-- gh-comment-id:2541957657 --> @S0AndS0 commented on GitHub (Dec 13, 2024): > ``` > Dec 13 07:35:34 <HOST> ollama[730]: time=2024-12-13T07:35:34.234-08:00 level=INFO source=routes.go:1274 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v12_avx]" > Dec 13 07:35:34 <HOST> ollama[730]: time=2024-12-13T07:35:34.906-08:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-962ca16e-d3f0-3dde-ecfd-3d968f5d2d4e library=cuda variant=v11 compute=5.0 driver=12.7 name="NVIDIA GeForce GTX 960M" total="3.9 GiB" available="3.9 GiB" > ``` > > This may be a build issue. The cuda variant of your device is v11 but there's no v11 runner in your package. Looking at the [ollama-cuda](https://archlinux.org/packages/extra/x86_64/ollama-cuda/) file list there's only a cuda_v12 runner. I suggest filing a ticket with the Arch ollama-cuda maintainers. Wow, thanks for the rapid response! Looks like the bug reports system for Arch requires getting permission, so I'll get on that next, and while waiting try find a non-broken version to downgrade to. > We recently merged build related changes that should make it easier for the Arch packaging folks to adapt to the new build. > > Until then, you can use the official ollama install guide: https://github.com/ollama/ollama/blob/main/docs/linux.md which will include the v11 runner and should work correctly on your system. > > #7499 Sensational! I'll give that a shot if Arch team, and/or downgrading attempts, take too long to get things functional again. ## Update 2024-12-13 13:00 -0800 I've got Issue [opened](https://gitlab.archlinux.org/archlinux/packaging/packages/ollama/-/issues/9) over at Arch! And _should_ update here once package maintainers got a fix sorted. Thanks y'all for the fast response and concise directions!
GiteaMirror commented 2026-04-22 10:56:07 -05:00
Author
Owner
Copy Link

@svenstaro commented on GitHub (Dec 15, 2024):

@dhiltgen Arch packager here. We already use those changes (see #7499).

What I don't understand: What do we need cuda 11 for when we have cuda 12? Can we even build the cuda 11 variant when we only have cuda 12?

<!-- gh-comment-id:2543410550 --> @svenstaro commented on GitHub (Dec 15, 2024): @dhiltgen Arch packager here. We already use those changes (see #7499). What I don't understand: What do we need cuda 11 for when we have cuda 12? Can we even build the cuda 11 variant when we only have cuda 12?
GiteaMirror commented 2026-04-22 10:56:08 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Dec 16, 2024):

What I don't understand: What do we need cuda 11 for when we have cuda 12? Can we even build the cuda 11 variant when we only have cuda 12?

For our official binary releases, we build both v11 and v12 to balance broad hardware and driver version support while supporting the best performance on newer GPUs and drivers. We haven't diverged yet, but the intent is to start enabling build flags on v12 that are only supported in newer GPUs/drivers. We've found driver 525 and older needs v11 to work properly.

We haven't set this part up to be build-time configurable yet, but here's the relevant code that detects if the v11 runner needs to be used
https://github.com/ollama/ollama/blob/main/discover/cuda_common.go#L60 This corresponds to https://github.com/ollama/ollama/blob/main/make/Makefile.cuda_v11#L8 and https://github.com/ollama/ollama/blob/main/make/Makefile.cuda_v12#L8 in the current makefiles. This code should probably be adjusted to detect if we only have 1 variant of cuda and just always use that.

<!-- gh-comment-id:2546129536 --> @dhiltgen commented on GitHub (Dec 16, 2024): > What I don't understand: What do we need cuda 11 for when we have cuda 12? Can we even build the cuda 11 variant when we only have cuda 12? For our official binary releases, we build both v11 and v12 to balance broad hardware and driver version support while supporting the best performance on newer GPUs and drivers. We haven't diverged yet, but the intent is to start enabling build flags on v12 that are only supported in newer GPUs/drivers. We've found driver 525 and older needs v11 to work properly. We haven't set this part up to be build-time configurable yet, but here's the relevant code that detects if the v11 runner needs to be used https://github.com/ollama/ollama/blob/main/discover/cuda_common.go#L60 This corresponds to https://github.com/ollama/ollama/blob/main/make/Makefile.cuda_v11#L8 and https://github.com/ollama/ollama/blob/main/make/Makefile.cuda_v12#L8 in the current makefiles. This code should probably be adjusted to detect if we only have 1 variant of cuda and just always use that.
GiteaMirror commented 2026-04-22 10:56:08 -05:00
Author
Owner
Copy Link

@loqs commented on GitHub (Dec 16, 2024):

How does ollama determine gpuInfo.computeMajor gpuInfo.DriverMajor gpuInfo.DriverMinor ? Is this from shared library probing? Would a debug log help?

<!-- gh-comment-id:2546257006 --> @loqs commented on GitHub (Dec 16, 2024): How does ollama determine `gpuInfo.computeMajor` `gpuInfo.DriverMajor` `gpuInfo.DriverMinor` ? Is this from shared library probing? Would a debug log help?
GiteaMirror commented 2026-04-22 10:56:09 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Dec 16, 2024):

How does ollama determine gpuInfo.computeMajor gpuInfo.DriverMajor gpuInfo.DriverMinor ? Is this from shared library probing? Would a debug log help?

The driver and compute information is retrieved from the cuda libraries (driver, runtime, or management) in https://github.com/ollama/ollama/tree/main/discover

<!-- gh-comment-id:2546365415 --> @dhiltgen commented on GitHub (Dec 16, 2024): > How does ollama determine gpuInfo.computeMajor gpuInfo.DriverMajor gpuInfo.DriverMinor ? Is this from shared library probing? Would a debug log help? The driver and compute information is retrieved from the cuda libraries (driver, runtime, or management) in https://github.com/ollama/ollama/tree/main/discover
GiteaMirror commented 2026-04-22 10:56:09 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Dec 16, 2024):

@svenstaro PR #8121 should help address this for your packaging. I think you may want to override CUDA_ARCHITECTURES at build time to pick up 50+ on v12.

<!-- gh-comment-id:2546370256 --> @dhiltgen commented on GitHub (Dec 16, 2024): @svenstaro PR #8121 should help address this for your packaging. I think you may want to override `CUDA_ARCHITECTURES` at build time to pick up 50+ on v12.
GiteaMirror commented 2026-04-22 10:56:09 -05:00
Author
Owner
Copy Link

@S0AndS0 commented on GitHub (Mar 13, 2025):

Quick check-in; I believe my Issue, technical issue that is, now be resolved by the mentioned PR as well as work done by Arch package maintainers! Or in other words, I believe it should be safe to close this issue and will do so now.

Thanks again to all those involved with sorting this out!

<!-- gh-comment-id:2722941642 --> @S0AndS0 commented on GitHub (Mar 13, 2025): Quick check-in; I believe my Issue, technical issue that is, now be resolved by the mentioned PR as well as work done by Arch package maintainers! Or in other words, I believe it _should_ be safe to close this issue and will do so now. Thanks again to all those involved with sorting this out!
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#30930
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?