HF install instructions don't work
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 48/100
- Issue type
- Bug
- Clarity
- Mostly clear
- Activity status
- Quiet
- Domain
- build-system, documentation
Research direction
Reproduce the Hugging Face install command in the reported Python 3.12.11 environment, then inspect the Cargo file and the published openai-harmony wheels and platform tags. Done means the documented vllm installation resolves successfully and the package metadata or instructions correctly references the available 0.1.0 release.
Written by the indexing model from the issue text.
Description
Congrats on the release! on HF it recommends installing vllm through:
uv pip install --pre vllm==0.10.1+gptoss \
--extra-index-url https://wheels.vllm.ai/gpt-oss/ \
--extra-index-url https://download.pytorch.org/whl/nightly/cu128 \
--index-strategy unsafe-best-match
which leads to the following error:
Using Python 3.12.11 environment at: /juice4/scr4/ahmedah/micromamba/envs/mem
× No solution found when resolving dependencies:
╰─▶ Because openai-harmony==0.1.0 has no wheels with a matching platform tag (e.g., manylinux_2_31_x86_64) and vllm==0.10.1+gptoss depends on openai-harmony==0.1.0, we can conclude
that vllm==0.10.1+gptoss cannot be used.
And because you require vllm==0.10.1+gptoss, we can conclude that your requirements are unsatisfiable.
hint: Wheels are available for openai-harmony (v0.1.0) on the following platform: manylinux_2_34_x86_64
but there is no tag for v0.1.0 only for 0.0.1 and 0.0.2. I just changed the Cargo file to say 0.1.0 but am I missing something?
- Dominant language
- Rust
- Stars
- 4.5k
- Forks
- 317
- PR merge metrics
- No merged PRs in 30d
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from openai/harmony
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
Rendering is quadratic in the length of a single messagePossibly taken @rksharma-owg claimed this 58 days ago. Open
Difficulty 4/5 3-5 days Newbie friendliness 55/100
-
Difficulty 3/5 1-2 days Newbie friendliness 25/100
-
Difficulty 5/5 Over a week Newbie friendliness 20/100
-
Python asyncio eventloop run_in_executor with ThreadPoolExecutor is not workingPossibly taken @Gnoale claimed this 219 days ago. Open
Difficulty 4/5 3-5 days Newbie friendliness 35/100
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
NSPG13/agent-bounties#1749 ·
Maintainers usually reply within 1 day
-
area: web bug
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
kinqsradio/orbyn-engineering#227 ·
Maintainers usually reply within 1 day
-
agentic-workflows automation repo-assist
Difficulty 1/5 Under an hour Newbie friendliness 85/100
shanselman/winget-tui#483 ·
Maintainers usually reply within 2 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
lightonai/next-plaid#205 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
apache/datafusion-iceberg#100 ·
Maintainers usually reply within 1 day