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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Cascade Attention for Flashinfer
- [Bug]: Draft model produces degenerate output (token_id=0) in speculative decoding with Qwen3-235B-A22B MoE target
- [Bug]: CUDA error: an illegal memory access was encountered when using turboquant and cuda graph on GB200
- [KVConnector] Remove `VLLM_DISABLE_REQUEST_ID_RANDOMIZATION` and auto-set it for PD
- [Bug]: DiffusionGemma chat logprobs can crash in batched requests
- [speculative decoding] fix dynamic SD with parallel drafting (PARD/P-Eagle) slot layout mismatch
- [RFC]: Fine-Grained Prefix Cache Hits for Hybrid Models
- Run Cohere2MoE shared experts outside FusedMoE for better prefill TTFT.
- [Feature]: Anthropic messages search_result content block support
- [Bugfix][V1] Warm up all top-k/top-p Triton sampler kernel specializations
- Docs
- Python not yet supported