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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Quantization] Fix INC/AutoRound GPTQ routing for group-misaligned TP shards
- [Core] Add token-budget-bounded early KV prefetch for waiting requests
- [Models] Cohere Eagle
- [Model] Support for Zyphra ZAYA1 models
- [Model][Gemma4] Support AutoRound/GPTQ quantized router and packed MoE weights
- [Frontend] Return rendered prompt text in chat completion response
- [CI] Narrow pytorch.yaml compile job source dependencies
- [feat] Add FP8 per-tensor Q scale support to Triton attention backend
- [CI] De-flake failure CI test "test_async_scheduling::test_without_spec_decoding"
- [ROCm][Bugfix] Re-tag AITER MoE weights as preshuffled after replace_parameter
- Docs
- Python not yet supported