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
- [2/N]Qwen3.5Opt: Add fused gate-sigmoid-mul-add kernel
- fix: recapture CUDA graphs for RL online weight updates
- fix: apply rope overrides to text_config for VLM-format models
- fix(loader): load all shards of a sharded GGUF checkpoint
- [tracing] Add a per-request cache-match snapshot (log + trace event)
- feat(spec): support NGRAM speculative decoding with DP attention
- [Fix] deepseekv32 detector: tolerate partial non-string param values raising MalformedJSON (stream tear-down)
- [DeepSeek-V4] Offload fp8 wo_a dequant to GPU to speed up weight loading
- fix(tokenizer_manager): give each parallel sample a distinct seed
- Fix support for PD (Prefilled Decoding) disaggregated deployment parameters in the Responses API.
- Docs
- Python not yet supported