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 supported50 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Clamp the kv-cache-memory advisory by memory allocated since startup
- [Bugfix][Core] Shut down executor workers when EngineCore init fails
- [Perf][DSv4.1] Reuse decode topk global indices across consumer layers
- [Bug]: NIXL P/D disagg silently corrupts output when hybrid-attention layers share a storage base with different block lengths (DeepSeek-V4.1-Flash)
- [V1] Add SamplingParams.hidden_state_window + position math for windowed hidden-state capture (#56916)
- [Bugfix][Core] Fix OpenTelemetry span ID collision across TP workers
- [RFC]: Raw-survivor storage with query-side rotation (RSQR) for KV cache eviction
- [Perf][DSv4.1] Native-head Triton sparse MLA for SM90 few-head prefill
- [Security] Reject Qwen3-Omni audio longer than the profiled duration
- [Bugfix][Scheduler] Refresh max tokens for streaming continuations
- Docs
- Python not yet supported