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
- Andrew/dflash2 experiment
- [Bugfix][Spec Decode] Don't swap the Gemma4 MTP draft into the target's VllmConfig
- [Bugfix][KV Offload] Size CPU cache slots for one KV group
- [DSpark] Support PP prefill with KV transfer (disaggregated serving)
- [Feat][Model] Enable KDA prefill checkpoints for GLM-5.3-Flash
- [Bugfix][GLM-5.3-Flash] Keep batch x heads out of gridDim.z in the GLM-5.3-Flash fused recurrent KDA kernel
- [Bugfix][V1] Handle shutdown during collective RPC
- [Bug]: SpecDecodingStats.num_drafts counts requests whose drafts were all invalidated
- [Bug]: Qwen3-ASR audio preprocessing produces different audio-token counts from Hugging Face
- [Spec Decode][Model] Support DFlash2 draft models with GLM-5.3-Flash
- Docs
- Python not yet supported