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] openai: End failed chat and completion streams with an error
- [Fix] dsv41: Support the minimal and medium reasoning effort levels
- [Fix] metrics: Do not count prompt tokens of requests aborted before forward
- [Feat] [diffusion] [NPU] Add support for HiDream-O1-Image (Dev-2604, Dev, Full)
- [Fix] frontend: Pass custom CA certificates to streaming requests
- [Fix] qwen4_exp: Capture DFlash aux hidden states on Qwen3.8-Flash-Next
- [Feat] [MLU] platform: Add initial support for Cambricon MLUs
- [Fix] model_loader: Fix state-dict post-processing, KV scale sync, and LoRA wrapper handling across non-default loaders
- [Fix] model_executor: Initialize idle metadata on the active attention backend
- [Feat] SenseNova-U1: CFG parallelism on two GPUs (1.95x, bit-identical)
- Docs
- Python not yet supported