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] fast_topk_v2 can silently return wrong top-k sets when a radix threshold bucket exceeds its 4096-entry candidate buffer (k=2048, long rows)
- [Bug] GLM-5.3-Flash cannot use FP8 KV cache: `index_kpool > 1` excludes `flashmla_kv`, and no CUDA DSA backend supports bf16-query x fp8-KV
- fix(security): bound top_logprobs_num, parallel sample n, and input_ids to prevent request-level DoS
- [cuda-graph] Index attention_layers by layer id (2/3)
- [Embed Override] Validate embed override hidden_dim at ingestion time
- Support deterministic inference for DeepSeek-V4
- [CPU] Add Nightly Test (Xeon) for large-model accuracy + performance
- feat: stagger ReplaySSM flush phases
- [Fix] Load FP8 KV-cache scales for Qwen3.5
- [Roadmap][Feature] Support T-Head PPU
- Docs
- Python not yet supported