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] Type-check request fields on /generate to prevent server crashes
- [cookbook] docs: add Intel Arc Pro B-Series (BMG) support to cookbook models
- Implemented MXFP4 quant lightning indexer for DSA
- [AMD] Run the DCP=1 verify prefix on MLA ASM as q_len=1 rows
- [Bug] DSpark SPS profiler mis-reads the attention-DP rank count from /server_info
- [Fix] Count attention-DP ranks in the DSpark SPS profiler
- [AMD] M2.5 Nightly Test Refresh
- [Bugfix] Load block-FP8 MoE TP shards that split checkpoint blocks
- [cake_kernels] minimax_h3 route: pass the engine's native operands to the fused stages
- [Feature] Paged Experts: serve MoE models whose weights do not fit VRAM
- Docs
- Python not yet supported