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] rust-server: Return named and required tool calls in non-streaming responses
- [Fix] spec: Apply the multi-layer boundary-KV fix to non-hybrid chain MTP drafts
- [Fix] spec: Keep chain MTP prefill hidden states under DP attention
- [Feat] [NVIDIA] deepseek-v4: add opt-in row-wise MoE pipelines
- [Feat] diffusion/realtime: Add a client-side benchmark for realtime video sessions
- [Fix] deps: add websockets so /v1/realtime works without extras
- [Fix] [AMD] kimi-k3: Restore the KDA in-proj fusion for quantized che…
- [AMD][Kimi-K3] Route radix4 on bf16 with the cached bias, drop the pe…
- [Fix] tokenizer: Isolate per-request failures and skip cancelled requests in AsyncDynamicBatchTokenizer
- [Fix] [AMD] layernorm: call vLLM fused_add_rms_norm in place
- Docs
- Python not yet supported