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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Spec Decode][Qwen4Exp] RecoverSSM for Qwen GDN and the PLE short conv
- [Docs] Add Granite 3.3 Instruct series to batch invariance tested models
- Updated TODO Doc in hadacore_transform
- [Security] Reject short Voxtral Realtime audio before the encoder
- [Bugfix][Model Loader] Restore kernel state post model loading via `TensorizerLoader`.
- [ROCm] AITER v0.1.23 bump: gfx950 a16w4 MXFP4 MoE Gluon backend crashes (AttributeError get_scaled_upcast_fp4_scale_layout)
- [Bug]: Greedy output changes between restarts, also with VLLM_BATCH_INVARIANT=1: the q/k-norm + RoPE combo kernel picks its reduction config by timing
- [Bugfix][Core] Count the external claim's state block in MambaManager admission
- [Docs] Document NIXL KV connector metrics aggregation semantics
- [RFC] RL Weight Update Roadmap
- Docs
- Python not yet supported