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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Qwen3-VL-235B-A22B-Instruct-FP8 tools doesn't respond in the tools but in content for hermes parswer
- [WIP] Calculate MFU/MBU for whole model forward pass
- [Core] Add per-request speculative decoding statistics to RequestOutput
- [Performance]: Manual Controlled GC
- [Feature]: About video input for qwen3vl
- [Misc] Pass reasoning to deepseekV32 tokenizer
- [Bug]: 5090 RTX seems to be broken
- [Bug]/[Feature]:NIXL Disaggregated Serving Fails with Pipeline Parallelism (PP > 1)
- [Kernel] add H100 triton fused moe config for FP8 Qwen3MoE
- [CI] Speed up sequence parallel tests
- Docs
- Python not yet supported