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 supported46 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: cuda graph takes too much memory for qwen 3.5
- [WIP] Prototype MM batcher interface
- [RFC]: Incremental MoE Expert Offloading — GPU Cache + Async Pipeline
- [RFC]: Multi-tier KV offloading via the vLLM offloading connector
- [CI] Swap to smaller models for MIG slice compatibility
- [Feature]: support affinity settings in helm chart
- [FlashLinearAttention] reduce recompilations by removing unused triton kernel inputs
- Upgrade to Transformers v5
- [ROCm][Test] Add hybrid block size and RDNA4 backend selection tests
- [Logging] Add JIT compilation progress log for FlashInfer
- Docs
- Python not yet supported