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
- [AMD] ci: port the AgentX GLM-5.2-MXFP4 agentic-coding MTP benchmark to MI35x nightly
- 【WIP】【NPU】Br npu pin cpu mirror
- [Bug] RuntimeError: Promotion for Float8 Types is not supported, attempted to promote Float8_e4m3fn and BFloat16
- fix(gemma4): set lm_head_is_tied in the unified model
- [Fix] Ignore stream flag for tokenize requests
- fix(metrics): gate scheduler stats logging on attn_cp_rank == 0
- [HiCache] Make cudaHostRegister idempotent and tolerate already-registered ranges
- [MiniMax-M3] Decode: paged K/V tile loads and a tiny GEMM for the router projection
- [NPU] Keep Qwen3-ASR fused kernels compile-safe under torch.compile
- [Bugfix] Reject non-leading system messages in the DeepSeek-V4 chat encoder path
- Docs
- Python not yet supported