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: broadcast EAGLE draft-side sampling across TP ranks on ROCm
- [Fix] Route text before the opening think token by position, not by index 0
- [Fix] Restore fused_shared_experts_scaling_factor on biased_grouped_topk_cpu
- fix(anthropic): use monotonic_time() for received_time to fix negative Prometheus metrics
- fix: remove duplicate words in comments
- fix: propagate rank-local tensor update failures
- [Kernel] DSv4 top-k v2: raw_indices output + adaptive cluster split
- [Bug] apply_rotary_emb_flat_kernel rotates and overwrites the columns past rope_dim
- [Fix] Mask the padded columns in apply_rotary_emb_flat_kernel
- [Fix] Normalize grayscale JPEGs in GPU image decoding
- Docs
- Python not yet supported