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
- [Feat] disaggregation: Support DeepSeek-V4.1-Flash CPU-buffer PD
- [Roadmap] Humming integration maintenance
- [Feat] disaggregation: Support GLM-5.3 CPU-buffer PD
- [Fix] openai: match tokenize reasoning effort to chat
- [Doc] hicache: Fix MLA expansion in HiCache design doc
- [Fix] cache: Roll back host slots when allocation raises
- [Perf] [AMD] moe: Add opt-in AITER MegaMoE-TP for eager TP MoE forwards
- [Feat] [Intel] mem_cache: Enable the HiCache Mamba host pool on XPU
- [Feat] weight-cache: Add --weight-cache-max-bytes to the daemon
- [Perf] dsv41: Reuse request groups from causal expansion
- Docs
- Python not yet supported