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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Support AsyncTP pattern matching for FlashInfer vllm.bmm_fp8 on Blackwell#27893
- [Tool Parser][2/3] Use self.tools instead of request.tools in tool parsers
- Fix json chat_templet parser
- [Feature]: fused RMSNorm + fp8 block quantized kernel in Helion
- fix(reasoning): MiniMaxM2ReasoningParser broken for M2.5
- [Bugfix] Respect max_output_tokens in Harmony tool-call loop
- [ZenCPU] AMD Zen CPU Backend with supported dtypes via zentorch weekly
- [Misc] Rename think_start_str/think_end_str to reasoning_start_str/reasoning_end_str
- [CT][FP8][Marlin] refactor CompressedTensorsW8A16Fp8 to use kernel abstraction
- Use Inductor for More Quant Fusion
- Docs
- Python not yet supported