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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Move DP sync to a dedicated CUDA stream
- [Triton][Spec Decode] Non-causal support + relax 3D-launch gate for multi-query verify in unified attention
- [Bugfix][Quantization] Fp8 family: match modules_to_not_convert by substring
- [XPU] Support FP8 block quantization in XPU scaled_mm kernel
- [Kernel] Optimize fused_add_rms_norm with software pipelining
- Add DeepSeek-V4 DCP decode support
- [Refactor] Extract _bucket_layers_by_page_size from DSV4 KV cache config
- [Bugfix] Fix DeepSeek-V4 init errors for compressed tensors
- [Model Runner V2] Enable all dense models for mrv2 [4/N]
- [Model Runner V2] Migration to support quantized model by default [5/N]
- Docs
- Python not yet supported