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
- [Test] lora: Check every Qwen3.5 LoRA module group against HF+PEFT
- [CI] lint: Normalize workflow paths in check_opt_in_ci_tiers on Windows
- [Fix] rerank: Drop duplicated "Value error" prefix from top_n validation
- [Fix] cuda-graph: Prevent M-dependent prefill logprob drift on Gated-DeltaNet models
- [CI] [AMD] nightly-benchmark: Run InferenceX's AgentX GLM-5.2 MXFP4 MTP curve on MI35x
- [CI] [NVIDIA] runners: Add a gated GB300 sanity workflow
- [Fix] [CPU] moe: Validate topk_ids range in fused_experts_cpu
- [Perf] gdn: Use the fused decode projection + Conv1D kernel on Triton-capable out-of-tree platforms
- [Bug] Cross-Tenant Oracle Leak via NGRAM Speculative Decoding Metrics in SGLang
- [Doc] observability: Document KV cache events and how to subscribe to them
- Docs
- Python not yet supported