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
- Batch DFlash/DSpark replacement prefills using observed request demand
- [Bugfix] Fix BF16 dtype and TP act-order w2 scales in GPTQ Marlin MoE
- [sglang-miles] Restore distributed LoRA under DP attention
- [PD] Add load-aware cache-off DP prefill routing
- Diffusion LoRA auto mode statically merges post-load FP8 weights and crashes
- perf(mamba): defer device free-list merging until allocation needs released slots
- [Bugfix] Fix CLIP text embedding batching
- fix(diffusion): do not statically merge LoRA into quantized weights
- [Apple Silicon] Add mps backend paged attention decode
- fix(hicache): support HF3FS with logical KV anchors
- Docs
- Python not yet supported