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
- [Perf] diffusion/cache: Prefetch tile digests so hashing overlaps the VAE encode
- [Perf] rust-server: Avoid raw state materialization for default /server_info
- [CI] [AMD] schedule: Run the ROCm 7.2.0 and 7.2.4 lanes on weekends only
- [Fix] mem_cache: Size a fused draft's KV region in the dtype the draft resolves
- [Fix] mxfp8: scope the triton_kernels parity check to 16-bit inputs
- [Fix] openai: Route a bare LoRA adapter name in `model` to the adapter
- [Bug][DeepSeek-V4.1][SM120] candidate_topk_blocks: 0 does not disable the candidate scheme: layers 24-39 silently lose all top-k candidates
- [Perf] [NPU] attention: Use QuantLightningIndexerV2 for DSA context parallelism
- [Chore] [AMD] monokernels: Pin sgl-amd-mono at bfd657ee
- [Fix] [Intel] gemma4-diffusion: Serve DiffusionGemma on Intel XPU
- Docs
- Python not yet supported