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] Abort only the request a rid names, not every rid it prefixes
- [AMD] integrate kimi k3 monokernel
- [NIXL] Support per-GPU UCX device selection
- [Fix] Mamba slot admission for the classic hybrid pool: gate the scheduler, never assert the engine
- [Bug] DSV4.1 Flash + DSPARK: CUDA caching allocator exhausts GPU memory under sustained max-batch decode (OOM crash every 15–25 min), KV pool only 29% used
- [openai] Expose opt-in per-request metrics in OpenAI-compatible responses
- [AMD] DeepSeek-V4.1: opt-in mono decode launches on gfx950
- [DSv4.1] Read FP8 caches directly on long-prefix prefill steps
- [AMD] DeepSeek-V4.1: fix four MegaMoE crashes at attention TP > 1
- [Bugfix] Propagate SwiGLU clamp to KT CPU experts
- Docs
- Python not yet supported