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
- [RL] DeepSeek V4 weight-update fixes: UE8M0 packed-scale shards, attn_sink cache refresh, per-process DeepGEMM cache
- [Bugfix] GptOssDetector: stop replaying streamed text and dropping tool calls
- [Simulator] Fix partial prefetch accounting and offline timeout semantics
- [Test] Wait for the SSL watcher to observe a change instead of racing it
- [NPU][HiCache] Fix MLA host pool crash with MTP draft pools
- [Bugfix] Detokenizer: keep sent_offset monotonic when a character is split across steps
- [XPU][CI] Activate the uv venv in the kernel release workflow
- [CPU] Add fp8 quantization ops with AVX10.2 runtime dispatch
- [Auto-Fix] Add XPU rotary-embedding dtype handling for StableLM-2 (fixes dimension mismatch)
- [PD] Arm host drain ack tracking before abort notification
- Docs
- Python not yet supported