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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Misc] Warn when --block-size is silently discarded by backend alignment
- [Bugfix][Spec Decode] Capture the widest uniform decode batch by default
- VLLM_ATTENTION_BACKEND env var is silently ignored — attention_backend= LLM()/EngineArgs kwarg is the only mechanism that works
- [Kernel][Model] Optimize FA4 mm_prefix range lookup
- [Test] Add per-parser tool-call format conformance tests
- [RFC]: Support Speculative Decoding with Decode Context Parallelism
- [Bug][PD][Mooncake] Client disconnect on decode node does not release prefill KV cache
- [Bug]: DeepGemm accuracy auto-disable (_DEEPGEMM_BLACKWELL_EXCLUDED_MODEL_TYPES) does not apply to the FP8 MoE path
- [BugFix] Scope divergent hybrid cache hits to capable connectors
- [Bugfix][Mooncake] Revalidate exact partial-hash hit boundaries
- Docs
- Python not yet supported