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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix(gemma4): handle missing k_norm.weight for KV-shared layers in both base and SFT checkpoints
- [BugFix] Fix extract_hidden_states CUDA graph padding polluting KV cache
- KV Cache MLA NaN Write Reporting
- [Performance]: Async scheduling on AMD hardware
- [Feat][rust-vllm] add log available router
- [Bug]: failed with AssertionError when using mooncakeconnector
- [Kernel][MoE] Add Sonic-MoE unquantized fused-experts backend
- [Bugfix] Fix CUTLASS MoE router input weighting for FP8/FP4
- [CI Fail] Fix flaky shutdown test caused by blocking event loop
- [Doc]: INT8 weight-only quantization causes 4x throughput regression at batch=1 on memory-bandwidth-bound GPUs
- Docs
- Python not yet supported