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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [MiniMax-M3 Performance] Prefer CuTe for MiniMax M3 FP8 indexer prefill
- [Perf][DSv4.1] Parallelize prefill Top-K/SWA index combination
- [Bugfix][MLA] Keep ds_mla cache-format canonicalization layer-local
- [Bugfix][Reasoning] Return unfinished K2 Horizon reasoning as reasoning
- [Docs] Clarify Mistral parallel tool call workaround in tool_calling.md
- SamplingParams accepts float for int fields (max_tokens/min_tokens/logprobs), then LLM.generate() hangs on an EngineCore msgspec decode error
- [Bugfix][EPLB] Record the load window by logical expert
- [Bug]: deepseek-v4-flash-0731 repeat and Garbled characters
- [Refactor][KV Offload] Split shared offload regions into concrete classes
- [Frontend] generate: packed top-k logprobs (packed_top_k_logprobs)
- Docs
- Python not yet supported