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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- # [Bug]: MinTokensLogitsProcessor indexes logits with global token ids — out-of-bounds when the LM head output is TP-sharded
- [Bugfix][Sampler] Support TP-sharded logits in MinTokensLogitsProcessor
- [Bug]: vLLM EngineCore crash in native KV offloading for hybrid Attention/Mamba model
- [Docs][KV Connector] Clarify NIXL metrics aggregation
- [Bugfix] Fix decoded logprob tokens that continue a split UTF-8 character
- [ROCm][Perf] MXFP4 indexer K cache for GLM-5 / DeepSeek-V3.2 DSA
- [Model][Spec Decode] Migrate HY V3 to the Flat Model layout
- [Kernel] ReplaySSM: cache SSM inputs for faster Gated DeltaNet standard decode
- [Quantization] Report the resolved kernel per layer in model inspection
- Skip out-of-window partial-tail store jobs instead of crashing EngineCore (#61970)
- Docs
- Python not yet supported