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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Frontend] Allow opt-in prompt id reuse without a KV connector
- [Core][KVConnector] Connector "ready" state for asynchronous connector startup
- [Bugfix][Attention] Accept split KV blocks in the b12x backend
- [ROCm][Kernel] Add W4A8 MoE decode kernel for RDNA3/RDNA3.5 (gfx11)
- [RFC]: [V1 Scheduler][KV Offload] Eliminate 1.0–1.8s Re-Queueing Stall for Completed Async KV Pulls via Front-of-Queue Re-Admission
- [ROCm][Quantization] Add load-time int4 lm_head quantization for RDNA…
- [Bugfix][Multimodal] Transfer pruning-adjusted M-RoPE state in disaggregated P/D
- [Model][Hardware][AMD] Fuse DSR1 Input Projection with Dual RMS + Quant
- [Bugfix][Spec Decode] Synchronize adaptive DSpark decisions across TP ranks
- [Bugfix][Pooling] Honor the CrossEncoder activation saved by Sentence Transformers v6
- Docs
- Python not yet supported