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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: CutlassW4A8LinearKernel fails on DeepSeekV3.1 W4AF8 due to dimension alignment (K=7168, N=2112 not divisible by 128)
- [Kernel][Helion][1/N] Add Helion kernel for dynamic_per_token_scaled_fp8_quant
- [KVConnector] Fix data race when we have both local and external cache hit
- feat(benchmark/kernels): add scaled_fp8_quant benchmark with multiple quantization modes
- [ROCm][FEAT] Integrate aiter gemm w8a8 ptpc
- add video [Model] Video Frame Sparsification via Pixel-Level Similarity for Efficient Multimodal Long-Video Inference for Qwen2.5_vl and Qwen3_vlsparse
- [Bug]: Loading Deepseek models is very slow
- feat: Use an executor to parallelize load of deepseek v2 based models (kimi, etc)
- feat(pooling/score): Enhance RerankRequest with optional instruction field and multimodal input support
- [BugFix] Fixed the argument name for the number of redundant experts in eep example
- Docs
- Python not yet supported