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] Don't route TOWER/CONNECTOR LoRA mappings to the language wrapper
- [Bug]: FULL cudagraph dummy runs set seq_lens > max_model_len, overrunning the block table (TRITON_ATTN illegal memory access; FLEX_ATTENTION shape error)
- [Spec Decode] Let the speculator build its own draft prefill attention metadata
- [Bugfix][Model Runner] Bound dummy seq_lens by max_model_len
- [RFC]: Decouple draft-model parallelism from the target model (PCP/DCP + speculative decoding)
- [Performance]: Avoid scanning the full KV block table
- [RFC]: Allow the DSA Indexer to Use Context Parallelism Independently
- [Performance]: Add native layer-fused MoE parameter loading for weight reload
- [Bug]: Qwen3-Omni deepstack drops embedding modality after torch.split, breaking use_audio_in_video
- [CI] Fix nixl harness teardown: TERM grace before SIGKILL
- Docs
- Python not yet supported