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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Spec Decode] Reduce TP communication for speculative decoding draft token generation
- [CI] Add P2pNccl integration test + rename nixl_integration to pd_integration
- [DO Not Merge Yet][Refactor] [1/N] Reorganize kernel abstraction directory
- [ROCm] update triton branch to support gpt-oss models for gfx11xx devices
- [Bugfix] Fix DP Attention Padding in Dummy Run
- add --insecure arg to the vllm bench to skip TLS
- [Perf] Optimize async scheduling redundant copy, 0.9% E2E throughput improvement
- [BugFix] Fix mm_encoder_only init for qwen3 vl moe model
- [ROCm][AITER] Add fused RoPE+KVCache pass with MultiOutputPattern fix
- [Kernel] [Helion] [5/N] Add Helion Autotuning infrastructure
- Docs
- Python not yet supported