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
- [Bugfix][Determinism] Refuse batch-invariant mode on the sparse indexer
- [KV Offload] Let unfinished requests keep the chunks they will resume from
- [Bugfix][Frontend] Keep the trailing parameter when qwen3 closes the function without it
- [Bugfix] Make Elastic EP commit cancellation-safe
- [Feature]: OutOfResources: shared memory (98304 > 65536) on Turing (SM75) — global attention layers with head_dim=512
- [Bugfix][Multimodal] Cap the DynamicVideoBackend sampling fps
- [NIXL][Metrics] Add push-mode registration-expiry and writer-loop-error counters (O1)
- [Bug]: RealtimeConnection leaks connection state and skips teardown on handshake exception or task cancellation
- feat: capture selected hidden-state rows for rollout windows and teacher scoring
- [RFC]: Encoder-Only Prefill in P/D deployment for DeepSeek V4.1 Flash
- Docs
- Python not yet supported