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
- Skip Mamba splitting during async KV load
- [Test] Add DeepSeek MTP parallel-load tests
- Improve offline embedding throughput for pooling models
- [XPU] Fix double-transpose in XPUFP8ScaledMMLinearKernel for W8A8 quant method
- [WIP][Model]Add parakeet tdt 0.6b v3 model
- [MyPy] Fix mypy for `vllm/lora`
- [Core][Refactor] scheduler: refactor prefill chunk alignment logic
- [Bug]: /wake_up fails with "'list' object has no attribute 'zero_'" on hybrid-SWA / Mamba / DeltaNet models (SM120, NVFP4) — only Gemma-4 interleaved-SWA survives
- Rework quantization_config to use QuantKey and allow for activation override
- [EPD] Add ECMooncakeConnector for encoder cache over Mooncake TransferEngine
- Docs
- Python not yet supported