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
- [Feat] thinking-budget: Decouple thinking budget from --enable-strict-thinking
- [Feat] sglang-processor: render Inkling as TMLv0
- [Bug] GLM-5.3-Flash on 8×H20 (TP8/EP8) with EAGLE: CUDA illegal memory access in run_eagle_verify → build_grammar_vocab_mask
- [Bug] qwen3_coder: one `strict: true` tool under tool_choice="auto" makes a non-strict zero-argument tool get invented arguments
- [Fix] weight_cache: Keep the EPLB expert layout in the daemon
- [Fix] eplb: Load all local replicas of each expert
- [Perf] kda: Capture the GLM-5.3-Flash FlashInfer KDA prefill in breakable prefill CUDA graphs
- [Kernel] fp8: add FlashInfer b12x MXFP8 dense GEMM backend for SM120/…
- [Refactor] memory-pool: Build DSA indexer host pools from buffer info
- [Refactor] memory-pool: Build unified page-envelope host pools from buffer info
- Docs
- Python not yet supported