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 supported46 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix: handle escaped <\\think> tags in reasoning parser (closes #36207)
- feat(openai): add per-request timing metrics and completion_tokens_deβ¦
- [Usage]: MoE flatten_tp_size should not unconditionally include dp_size β DP loses its original semantics for MoE layers
- [Bug]: Qwen3.5 4b incompatibility
- [Core] Add --tensor-parallel-size-attention for TPA separation
- [Bug]: Generation hangs until RAY_CGRAPH_get_timeout (300s) with Ray compiled DAG executor
- Feat/sigint graceful shutdown
- bytes calculation for weight offloading
- [Attention] PCP alternative implementation
- [ROCm] Add cascade attention support for AITER FlashAttention backend
- Docs
- Python not yet supported