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
- [mem_cache] Free a chunked prefill's out-of-window SWA slots before sizing its next chunk
- [MLX] Compute prefill logits for the last position only
- [Fix] Honor temperature in SequenceClassification setwise scoring
- [Spec][DP] Skip the per-rank eager-draft fallback for a missing DSA seed under DP attention
- [Scheduler] Add --chunked-prefill-reserve-tokens
- [sglang-miles] Recover disk-delta checkpoints safely across resets and retries
- [Fix] Match DeepSeek-V4.1 KV capacity to physical layouts
- [AMD] fix: give JIT kernels real fp8 types on gfx950
- AMD: tune gfx950 sparse MLA decode launch shapes
- [AMD][ROCm] Keep cos_sin_cache fp32 on HIP for fused QSA indexer kernel
- Docs
- Python not yet supported