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
- [Bugfix][ROCm] Fix vllm fused_add_rms_norm 6-arg crash on non-AITER path
- [DFlash] Fix hybrid recurrent-state commit for radix cache
- [DFlash V2] Add configurable target verify budget
- [Fix] Preserve caller-owned hidden_states in DeepGemm standard pre-permute
- [Kernel] Add fused SiLU+clamp+mul+FP8 quant AOT kernel for DeepSeek V4 EP MoE path
- [Fix] Lazy-load SM100-only GDN BF16-state kernel so FlashInfer GDN works on Hopper
- [AMD] Register the Helios release workflow
- perf(spec): skip FlashInfer draft verify mask allocation
- fix(gateway): use per-DP-rank loads for power-of-two routing
- Add cache-agnostic in-batch prefix defer baseline
- Docs
- Python not yet supported