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
- [RFC] Agent-Aware KV Cache Phase 1 for Agentic Workloads
- Add per-commit PD disagg CI test for DSV4 on B200 (NIXL)
- [DLLM] Onboard Nemotron-Labs-Diffusion model with FastDiffuser decoding
- [session] Fix reaper closing sessions mid-decode; forward session_params in /v1/completions
- Add hard AIME25 subset tool
- Add Top-nĪ logit truncation custom logit processor example
- [Bug] GlmMoeDsa (GLM-5.2) FP4 + EAGLE: illegal memory access in flashinfer_trtllm bf16 batched-GEMM (nextn draft MoE); triton nextn default is HIP-gated after #30137
- [RL] Add /pull_weights: engine-side pull of published weights into a host-local checkpoint
- feat(tokenizer): tokenize chat prompts once instead of twice
- [grok2] Fix silently incomplete expert weights when tp_size < presharded checkpoint width
- Docs
- Python not yet supported