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
- [dLLM] Support DiffusionGemma decision APIs (stack 2/4)
- [Fix] Gemma 4 vision pooler: mask padding patches and scale in float32
- [EPLB] Add --eplb-max-rebalance-count to freeze the expert layout after K rebalances
- [Fix] disaggregation: Reuse startup decode graphs across PD role switches
- [Bug] Mistral tokenizers: image prompts lose <s>/[INST]/[/INST], and "[/THINK]" encodes as 5 tokens
- [Fix] Mistral: map control tokens back to ids on the multimodal text path
- [AMD][CI] Drop tc_piecewise split-op cases on ROCm and run the breakable ones
- [dLLM] Add DiffusionGemma prefix regression reproducer (stack 3/4)
- [HiCache] Fix DSA direct-linker assembly with skipped top-k layers
- [GLM5.3 Flash] Support CP/BCG prefill PD with DFlash2
- Docs
- Python not yet supported