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] trtllm_mha: include draft-extend-v2 in the native-FP4 forward_extend gate
- [Feat] deepseek_v4: Add bounded host Engram prefetch and chunked loading
- [CI] unit-test: Run the fused FP8 writer HIP test in the CPU suite
- [Fix] dsa: Isolate masked KV rows in FP8 TileLang attention
- [Fix] data-parallel: forward scheduler SIGQUIT through controller
- [Fix] [XPU] baichuan: Apply ALiBi slopes on intel_xpu
- [Test] diffusion: drain the VAE stream before asserting it is idle in test_overlap_and_serial_vae_inputs_match
- [Perf] [NVIDIA] deepseek-v4.1: Score only candidate positions in prefill indexer consumers
- [Feat] bench: Add `bench_engine_steps.py` for steady prefill and decode step cost
- [Fix] mem-cache: Retain SWA behind the replay-trimmed prefix frontier
- Docs
- Python not yet supported