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
- [CI] diffusion: update codeowners
- [Feat] benchmark: Support embedding JSONL inputs
- [Fix] distributed: Prevent unavailable PyNccl enablement
- [Perf] [AMD] qwen3.5: Fuse self-attn prepare on gfx950 (norm+RoPE+gate)
- [Fix] [NVIDIA] kvcache: Gate fused FP8 prefix-valid commit kernel on SM89+
- [Doc] [NPU] deepseek-v4-flash: Document DSpark and Compact deployment
- [Bug] Unauthenticated Mooncake Decode registrations can exhaust Prefill memory and cause inference denial of service
- [Bug] Unauthenticated Mooncake STAGING_RSP chunk index causes Prefill scheduler OOM
- [Perf] [NVIDIA] muse-spark: column-split the pooler and small-M unpooler on Hopper
- [Perf] unified_cache: Dedup the replicated MLA KV of Kimi K3 in the UMBP direct linker
- Docs
- Python not yet supported