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
- fix: shrink --hicache-size budget for SIDECAR draft host pool
- Fix FlashInfer MHA one-shot DP-attention padding
- [mem_cache] Honor the pool device for speculative mamba caches
- fix(unified-cache): improve load-back pin handling
- [CPU][Test] Guard the intel_amx verify seq_lens fix and re-enable EAGLE3 CPU parity
- [Bugfix] Fix Qwen3.5 MTP compressed-tensors ignore matching
- [MiniMax-M3][AMD] Fix EAGLE3 TARGET_VERIFY on gfx950
- EncoderScheduler dispatches requests after request timeout
- fix: skip timed out encoder requests
- [LMCache] Register fused MLA KV buffer over multi-process
- Docs
- Python not yet supported