If you get some weird compilation error(/lib/cmake/hip/hip-targets.cmake not found) and you want to do rocm, make sure you don't have hip-runtime-nvidia installed.
Search Criteria
Package Details: python-vllm 0.12.0-1
Package Actions
| Git Clone URL: | https://aur.archlinux.org/python-vllm.git (read-only, click to copy) |
|---|---|
| Package Base: | python-vllm |
| Description: | high-throughput and memory-efficient inference and serving engine for LLMs |
| Upstream URL: | https://github.com/vllm-project/vllm |
| Licenses: | Apache-2.0 |
| Submitter: | envolution |
| Maintainer: | envolution |
| Last Packager: | envolution |
| Votes: | 2 |
| Popularity: | 0.006515 |
| First Submitted: | 2024-12-01 16:07 (UTC) |
| Last Updated: | 2025-12-03 13:53 (UTC) |
Dependencies (56)
- numactl (numactl-gitAUR)
- python-aiohttp
- python-blake3AUR
- python-boto3 (python-boto3-gitAUR)
- python-cachetools
- python-cloudpickle
- python-diskcacheAUR
- python-fastapi
- python-ggufAUR (python-gguf-gitAUR)
- python-huggingface-hub (python-huggingface-hub-gitAUR)
- python-importlib-metadata
- python-msgspec
- python-openai
- python-opencv (python-opencv-cuda)
- python-partial-json-parserAUR (python-partial-json-parser-gitAUR)
- python-prometheus-fastapi-instrumentatorAUR
- python-psutil
- python-py-cpuinfo
- python-pybase64AUR (python-pybase64-gitAUR)
- python-pydantic
- Show 36 more dependencies...
Required by (3)
- python-pydantic-ai (optional)
- python-pydantic-ai-slim (optional)
- python-vllm-omni
Sources (1)
Latest Comments
« First ‹ Previous 1 2
amstan commented on 2025-03-28 05:42 (UTC) (edited on 2025-03-28 06:02 (UTC) by amstan)
amstan commented on 2025-03-28 05:37 (UTC)
Seems to be missing python-setuptools-scm.
envolution commented on 2024-12-01 16:08 (UTC)
Sadly this won't build without detecting cuda and tools - this is the CPU only build
Pinned Comments
envolution commented on 2025-08-04 01:31 (UTC)
@nipsky looks like some new incompatibility with python 3.13 - I was able to reproduce. Unfortunately the only feasible method at the moment is to run in a virtualenv using python 3.9-3.12. Upstream is working on 3.13 support but it's not quite there yet.
To be honest, we'll probably be on 3.14 by the time they support 3.13. I'll try have a look to see if I can patch it to initialize, but this week is kind of busy for me so it wouldn't be quick.