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
- https://github.com/sgl-project/sglang/issues/10038[Bug]
- [AMD][DSV4][SWA-BITEXACT 1/5] Extension points for strict SWA state capture/restore on unified_kv + HiCache
- [AMD][DSV4][SWA-BITEXACT 2/5] Host pools and L3 namespacing for strict SWA offload on unified_kv + HiCache
- [Feat][GLM-5.2] Shared KV Cache for Prefill and Decode
- feat(srt): add ProductionDebtInferenceGate and TechnicalDueDiligenceLedger
- [sglang-miles] Fix p2p weight registry: draft worker overwrite, fused indexer mapping, registration retries
- [Perf] Evaluate enc-dec cuda-graph gate on encoder_lens_cpu mirror
- [Diffusion][AMD] Add gfx1250 detection and stop silent CPU fallback for diffusion
- [Fix] flashinfer_mla: use flashinfer native fp8 MLA on SM90 instead of per-layer full-pool bf16 cast
- [Bug] Intermittent CUDA device-side crash with DSPARK speculative decoding on DeepSeek-V4-Flash-0731
- Docs
- Python not yet supported