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
- [Bug] Prefill breakable CUDA graph reuses weak-ref'd break inputs across buckets → wrong greedy output / IMA; e2e validation of #37448
- [Diffusion] Accumulate chunked LoRA merges with addmm
- [diffusion] perf: FastH3 8-Step V2 native support, native Blackwell VSA, batched H3 VAE decode
- [Bug] GLM-5.3-Flash: CUDA OOM in fp8_mqa_logits during long-context prefill kills all TP ranks
- [moe] Deal simulated round-robin experts rank-first so no EP rank idles
- [Fix] FA3: size k/v descale from cu_seqlens_q
- [Tracking] GLM-5.3-Flash on SM120: required fixes, carry status and release qualification
- [Bugfix] Fix Gloo collective mismatch in disagg prefill bootstrap when TP/CP > 1
- [Bug] DeepSeek-V4-Flash-Vision-Exp on 2x DGX Spark: scheduler OOM-killed during weight load (cookbook cell dgx-spark|flash-vision|fp4)
- Support sliding window and per-head sinks in Triton varlen prefill attention
- Docs
- Python not yet supported