vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- use split_group for pytorch process group creation
- [Bugfix] Fix TOCTOU port race in MultiprocExecutor (data_parallel_size > 1)
- [Bugfix] Extend compressed-tensors ignore for Qwen3.5 MTP experts
- [Bugfix] Fix Gemma4 MTP streaming multi-tool calls
- Inv rope fp8 quant
- [Bugfix] Fix LOGITPROC_SOURCE_ENTRYPOINT test to use spawn-compatible dist-info registration for XPU/ROCm
- [Performance] Bypass vllm_ir custom op wrap when only native impl is registered
- Use `pre-commit / pre-run-check` to gate docs build too
- [CI] Narrow misc.yaml source dependencies
- Add Laguna-XS.2-FP8 to gsm8k
- Docs
- Python not yet supported