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] Preserve structured values in qwen3_coder mixed unions
- [Fix] MiniMax-M3 streaming: stream null and empty tool arguments as non-streaming parses them
- [Fix] mm: encode a multimodal item once per request in chunked prefill
- [Feat] [AMD] dsv4: Dispatch Mega-mHC prefill to aiter on gfx950
- [AMD] Preserve JSON text in RPD trace export
- [Perf] Autotune low-M BF16 GEMMs via FlashInfer CuTe DSL on Blackwell
- [Bug] Request-controlled GLM-V video budgets can bypass deployment limits before decoding
- [Bug] Qwen-VL decodes full-resolution video frames before applying the final pixel budget
- [Bugfix] Restore DeepGEMM warmup state after failures
- [Multimodal] Keep Pillow's decompression-bomb guard in NanoNemotron processor
- Docs
- Python not yet supported