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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Doc][MoE Refactor] Fused MoE design doc
- [Doc] Fix 'douby' -> 'doubly' typo in prefix caching diagram titles
- [GGUF] Add IQ4_NL MMQ kernel support
- [Bug]: [V1] `prompt_tokens_details` always `null` in API response despite `--enable-prompt-tokens-details` (14+ months, incomplete fix in PR #18149)
- [Test][V1] Add sleep/wake correctness regression test for hybrid GDN/…
- [Feat] Add fast EP scaling with NCCL communicator split
- [Usage]: vLLM logs orjson warning
- fix: ensure missing CLI arguments don't cause KeyError in chat example (closes #44827)
- [Bugfix] Fix structured outputs FSM desync with pipeline parallelism on the V1 model runner
- [Bugfix][ROCm][FLA] Fix Triton compilation crash with num_stages=4 on AMD
- Docs
- Python not yet supported