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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Doc] Clarify NIXL backend selection
- [Bug]: Generation Hang after a while when using RayExecutorV2 cross two nodes with VLLM v0.24.0
- [Bugfix] Bound tile-local argmax to vocab_size in samplers
- [Bugfix] Fix CUDA graph profiling for long GDN warmups
- [Doc]: recipe for MiniMax-M3- crushes on 8xH200
- [Feature] Add Prometheus metrics for multimodal preprocessing pipeline
- [Core] Mix per-prompt seeds into seeded SamplingParams in the offline API
- [Bugfix] Reject --renderer-num-workers > 1 with mm cache for generation models
- [Core][Spec Decode] Add lookahead-aware prefix cache hashing for EAGLE-style draft models
- [RFC]: Cutting P/D-disaggregation TTFT: first-token seeding, fast KV side channels, and concurrent router dispatch (NixlConnector)
- Docs
- Python not yet supported