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] moe_sum_reduce: gate the bf16 vectorized path on hidden % 16
- [cherrypick from #42890] [Feature] Return output top logprobs as flat base64 arrays on request
- [AMD] Add Kimi-K3 Gluon whole-layer KDA and attention kernels
- [mem_cache] Unified SWA eviction: reclaim a branch's last window last
- [Inkling] Render and parse Chat, Responses and Anthropic APIs through tml-renderers
- [ROCm] Test residual gate eager fallback
- [Spec] Sample from the target when the rejection residual is empty in TreeSpeculativeSamplingTargetOnly
- [Fix] Materialize contiguous int64 indices in the fused mamba conv-slot kernels
- [Spec][DSpark] Opt-in fused int8 Markov walk kernels (Hopper)
- [DSv4.1] Speed up the FP4 indexer scorer by decoding keys without exp2
- Docs
- Python not yet supported