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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Minimax m3 gfx950 mxfp4
- [Frontend] Support additional sampling parameters for translation API
- [Bug]: Kimi-K2.6 VIT attention dispatch asserts on SM120 in flash_fwd_sm100
- [Kernel] Manual TP fusion via ResidualStream (AR+RMSNorm+quant)
- [Feature]: Wire swiglu_limit from model config into MoE kernel dispatch for DeepSeek V4 and other models
- [Feature]: Performance Optimization for Deepseek V4
- [Bug]: Integer overflow in moe_wna16.cu
- [Bug]: Kimi K2.5 garbage output with default flashinfer cutlass linear backend when flashinfer autotune enabled with full and piecewise cuda compilation
- [Rust Frontend] Add static HTTPS and mTLS support for HTTP and gRPC
- [ROCm] Minimax m3 mxfp4 on 45794
- Docs
- Python not yet supported