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
- [Bugfix][Attention] Check draft model support for FlashInfer large pages
- [CI] Automate dependency updates with hashes and a 7-day cooldown
- [Core][KVConnector] Don't wait on retained KV exports during cache-preserving keep pauses
- [Perf][Attention] DiffKV: split the 192-wide QK dot instead of padding it to 256
- [Bugfix][Kernel] Restore Qwen2 key-bias scores for int4 KV cache
- [Bugfix] Honor Qwen3-Next routed gate quantization
- [Spec Decode] Map Cosmos3-Edge DFlash aux layers onto split blocks
- [ROCm][Perf] Kimi-K3: token-sharded residual stream for long prefills
- make pf take configs instead of a bunch of args
- [ROCm][Perf][MiniMax-M3] Fused sparse-layer decode (mono decode kernel)
- Docs
- Python not yet supported