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 Gemma4 null and exponent tool argument types
- [Fix] Reject removal of an external corpus while its load is pending
- [Feature] Support API keys from secret environment variables
- [HiCache] Allow independent DeepSeek V4 SWA host ratio
- [cake_kernels] dsa_indexer route: DeepSeek-V3.2 lightning-indexer logits (ragged + paged) through FlashInfer dense_mqa / paged_mqa
- [Feature] Support Whisper speech translation (task="translate" / /v1/audio/translations)
- [Fix] Track partial weight updates per runner
- [Fix] Validate weight-cache memory operations before changing state
- [Fix] server_args: Expose DP scheduler rank count
- [Bug][ROCm] FLUX.2-dev fails on gfx1151: NVIDIA PTX inline assembly in residual_gate_add kernel
- Docs
- Python not yet supported