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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- support mxfp8 dispatch
- Pin AITER for 1250 build
- [Bugfix] Initialize per-token-head KV scale regions once per storage
- [Bug]: DeepSeek-V4-Flash-0731 crashes on RTX PRO 5000 because FlashInfer cannot reshape a tensor with 0 elements into the shape [0, -1]
- [Rust][Benchmark] Fix multi-turn input token accounting
- [Bugfix] Validate cached QuTLASS revision before reuse
- [Bugfix] Embed the full batch in the prompt_embeds path so LoRA metadata stays in range
- Fix GPT-OSS weight loading for DP and EP
- [Performance][Hardware][RISC-V] Use RVV FMA in FP32Vec transcendentals and the INT4 GEMM
- fix(security): restore incremental marker search cursors in thinking budget state
- Docs
- Python not yet supported