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] deepgemm: Handle missing CUDA toolkit during availability checks
- [Fix] qwen3_coder: Keep non-finite numbers out of number parameters
- [RFC] KV Cache Optimization for Cosmos3-Nano-Sim-Bimanual
- [Perf] [AMD] deepseek-v4.1: Run the HIP sparse prefill on the FP8 KV cache
- [Fix] [AMD] dsv4: Let breakable prefill graphs capture without the SWA tail
- [Bug] fused_marlin_moe is not run-to-run deterministic on sm_90+ (atomic adds, moe_align_block_size token order); --enable-deterministic-inference does not cover it
- [Fix] function_call: Infer number for schemas that allow integer or number
- [Fix] qwen3.5: Fix encode server initialization bug.
- [Perf] [AMD] mla: Use the gfx950 aiter RoPE, RMSNorm and MLA KV-row paths on gfx1250
- [Perf] hicache: Reduce host compaction copies by filling holes from boundary pages
- Docs
- Python not yet supported