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
- [MLX] Fix decode-KV pool sync writing to unallocated or stale slots
- [GDN] perf: Fuse the linear-attention prefill prologue for Flashinfer prefill attn
- Remove stale non-Standard-GQA gate for Nemotron BCG
- Replace ngram FULL_MASK Python for-loop with Triton kernel
- Fix follow-bootstrap-room routing with reserved DP slots
- [configs] Backfill DeepSeek V4 compress_ratios from compress_rates
- [XPU] Support decode context parallelism (DCP) on Intel XPU
- Support Structured Outputs with enable_thinking=False in Qwen3
- [VLM] Refactor video processing to fully async mode
- Integration with elasticmem
- Docs
- Python not yet supported