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
- [Feat] dflash: Support Bolt E4B NVFP4 DFlash checkpoints
- Update dsv4-flash mix in 950 testcase
- [Feat] disaggregation: Add opt-in Mooncake TENT transfer engine backend for PD
- [Feat] [NPU] attention: Support modelslim MLA FP8 KVCache
- [Perf] [XPU] quantization: Run block-FP8 linears weight-only (W8A16) on Xe2
- [Feat] scheduler: Add PrefixWeave scheduling policy
- [Perf] diffusion: Cosmos-Dreams rollout-owned prefix K/V buffer
- docs: fix 'maxium' typo in post-training integration page
- [Fix] kernel-plugins: Serve the MSA plugin behind --enable-nvidia-megakernel
- [Fix] scheduler: Skip --prefill-decode-interval when nothing is decoding
- Docs
- Python not yet supported