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] [AMD] Kimi-K3: KDA verify with fused ring, BF16 state, fused o_norm + o_proj
- [Perf] [AMD] Kimi-K3: DFlash draft split-KV sliding-window verify kernel
- [Perf] [AMD] Kimi-K3: MLA prefill cat-cache, absorb, prefix no-cat, FP8 prefill
- [Perf] [AMD] Kimi-K3: MLA verify on-device Gluon/HipKittens switch
- [Perf] [AMD] Kimi-K3: fused MoE routing, sort, quant and epilogue
- [Perf] [AMD] Kimi-K3: static FP8 dense layers and tuned decode GEMMs
- [Perf] [AMD] Kimi-K3: DFlash prep/tail graphs and fused post-verify
- [Perf] [AMD] Kimi-K3: fuse attention-residual aggregation with TP collectives
- [Fix] spec: Keep mixed-batch grammar masks in step; sample-verify fixes (DFlash)
- [Bug] InternlmDetector drops every streamed tool call after the first
- Docs
- Python not yet supported