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
- [Perf] multimodal_cache: reuse precomputed combined_hash in MultiModalStaticCache.get
- [Perf] sampling: Warm up the FlashInfer sampling module at server startup
- [Perf] managers: reduce temporary buffers in expert base64 encoding
- [Feat] logprobs: Allow flat output top logprobs on streaming /generate
- [Fix] [CPU] Fix: Qwen3.5-35B-A3B-GPTQ-Int4 quantization rule failure and accuracy degradation
- [Fix] deepseek: fix stale kernel_api_logging import breaking AWQ weight loading on CUDA
- [Feat] rust-server: DeepSeek-V4.1 images via deepseek-recipe
- [Feat] sglang-processor: GLM-5.3-Flash image preprocessing
- [Fix] mimo: Keep tool calls with nullable schemas, overflowing numbers, or batched stream chunks
- [Fix] Responses: keep late instructions in place on the merge path
- Docs
- Python not yet supported