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
- [Bugfix] Fix DeepGemm warmup OOM from DP world_size multiplication
- [WIP] Switch vLLM to The Rock when on AMD hardware
- [Core] Balance padding vs group count when grouping hybrid KV cache layers
- [Bugfix] Fix MiniMax-M3 ModelOpt FP8 MoE SwiGLU params
- [Bug]: Failed to run RedHatAI/gemma-4-31B-it-speculator.dspark
- [Bugfix][Spec Decode] Enable Step-3.7-Flash (Step3p7) MTP on Model Runner V2
- [Bug]: Harmony models reject namespace tool type in Responses API
- [Performance] Skip redundant full-fit admission pass
- [Bugfix][Frontend] Prevent server_load double-decrement on client disconnect
- [Feature]: Make Ray placement group strategy configurable via VLLM_RAY_PG_STRATEGY
- Docs
- Python not yet supported