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] diffusion: Fuse LTX-2.3 vocoder resampling and SnakeBeta
- [Perf] diffusion: Cache FLUX.2 Klein reference K/V across steps
- [Doc] cookbook: Install MiniMax-M3.1-Flash from main and move GB / Hopper to nightly images
- [Feat] [Intel] video_decoder: Decode video on the XPU media engine via torchcodec-xpu
- [Fix] fp8_utils: Import DeepGEMM lazily in transform_scale_ue8m0
- [Fix] moe: Preserve expert recording with TRT-LLM routing
- [Fix] Mooncake: Resolve per-worker MNNVL physical GPU
- [Test] cp: Add a diagnostic for the CP8 TP-decode logprob gap (do not merge)
- [Fix] function_call: Reject complete invalid Qwen JSON tool calls
- [Feat] mem_cache: Elastic hybrid-SWA KV pools (kvcached VMM), with an Intel XPU path
- Docs
- Python not yet supported