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
- # [Bugfix]Fix indexError in moe wna16 quantization with enable-expert-parallel
- [Performance]: non-optimal performance of `linear` for medium batches
- [Feature] TRITON_MLA: support FP8 KV cache (needed for SM12.0 / Blackwell)
- [Misc] Replace bare AssertionError with specific exception types
- [ROCm][Quantization] Enable moe_wna16 on ROCm via Triton fallback
- [Bugfix] Fix RoutedExpertsCapturer for pipeline parallelism (PP > 1)
- [Bugfix] Fix Triton attention layout when used in combination with the NIXL connector
- Fix MIG UUID handling in interface.py and cuda.py
- Fixed import error of a test
- [WIP] Full CI test run with Model Runner V2
- Docs
- Python not yet supported