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
- [Model Runner V2] Optional post-capture warmup of every decode batch size, logits row count and graph size
- [Bugfix] Keep the MiniCPM-V-4.6 vision tower unquantized for GPTQ and AWQ checkpoints
- [Model][MiniMax-M3] Split-KV indexer prefill scoring and sync-free prefill metadata
- [Model][MiniMax-M3] Context-parallel indexer decode scoring across TP ranks
- [XPU][Spec Decode] RecoverSSM: route Qwen GDN through the Triton/FLA core on XPU
- [Spec Decode][Mamba] RecoverSSM: support pipeline parallelism (non-last ranks commit in the deferred PP postprocess)
- [Startup] Add an opt-in FlashInfer MoE search strategy
- [Build] Re-fetch DeepGEMM when the cached checkout is not the pinned commit
- [Bugfix] Free the pinned CPU weight backup on wake_up
- [Bug]: OffloadingConnector with LHBNC returns wrong output on CPU hits
- Docs
- Python not yet supported