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
- [bugfix] DeepSeek MTP support and Pipeline Parallel feature.
- [EPLB] Mask padding in EPLB load recording
- [WIP] Remove kv cache dtype enum from csrc
- [Bug]: qwen3 235B model with latest vllm is going to generate only 1 token.
- [Draft][MRV2] Experimental `build_attn_metadata` refactor
- Qwen3.5 0325 mtp
- [feature] Implement reasoning_effort
- MiniMaxM2ReasoningParser broken for M2.5: extract_reasoning_streaming assumes no <think> start tag
- [MoE][GPT-OSS] Add L40S/SM89 Marlin block-size policy
- feat(quantization): fix W4A8-INT activation quantization and int4 support in Marlin kernel
- Docs
- Python not yet supported