sglang
https://github.com/sgl-project/sglang
Python
SGLang is a high-performance serving framework for large language models and multimodal models.
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 supported1 Subscribers
Add a CodeTriage badge to sglang
Help out
- Issues
- [fix] prefill CUDA graph fallback returning a runner instead of GraphCapture
- [Perf] [AMD] aiter: Run the DSpark MHA draft on non-causal unified_attention
- [Fix] [AMD] Keep QK-norm RoPE shuffles within logical warps
- [DSV4] Fix CUDA Cluster top-k tie overflow exactness
- [Docs] [AMD] Add MiMo-V2.6 MI355X INT4 QuickReduce recipe
- [Fix] diffusion: Build the Cosmos 3 RoPE table on GPU so CPU offload gives the same output
- [Bug] NemotronHConfig rejects transformers 5 layer types `linear_attention` / `full_attention` in config.json
- [Perf] [AMD] kimi-k3: Fuse attention o_proj's GEMM with its attention-TP sum via mori
- [Perf] kda: Write prefill convolution into contiguous QKV groups
- [Perf] kimi-k3: Allow residual bank shards with NCCL
- Docs
- Python not yet supported