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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Core] Optimize PriorityRequestQueue with lazy deletion
- [Bugfix] Fix DP port conflict during distributed initialization
- [Perf] Fuse hidden states scale transpose with quant for FP8 Trtllm MoE
- [Bugfix] Fix ngram spec decode corrupted output on hybrid GDN models
- [Model] Add IsHybrid support to Qwen3_5MoeForCausalLM
- [CPU] Fix nobind mode to distribute OMP_PLACES across tp workers
- [EPLB] Add a shutdown mechanism for the Async EPLB worker
- add HyperCLOVAX tool & reasoning parser
- support hybrid attention for mooncake
- [Bug]: Runtime error on ROCm platform serving Deepseek-R1 using VLLM_ROCM_USE_AITER=1
- Docs
- Python not yet supported