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 AITER DSA output allocation for FP8 queries
- fix(spec): stop custom_mask unbounded growth via torch.cat
- ci: pass PR branch name through env, not `${{ }}`, to close a command injection on the self-hosted CI runners
- Support Mooncake L3 storage under DSA cache layer split
- [Spec] Allow pipeline parallelism with speculative decoding on the PD-prefill role
- [Fix] Share the MTP draft's embed/lm_head before the KV pool is profiled
- Enforce parallel_tool_calls=false at parse time for unconstrained tool emissions
- [HiCache] Add storage-preserving flush for UnifiedRadixCache
- [AMD][DSV4] perf: tuned FlyDSL fp4 indexer score on MI355X
- test(hicache): cover buffer pipeline idle flush gate
- Docs
- Python not yet supported