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
- [Bugfix] FlashInfer autotune cache dropped every startup under expert parallelism
- [DSV4.1][PD][7/N][Perf] Reuse shared compressed KV dequantization in DeepSeek V4.1 CP prefill
- [FIX] Avoid eager Megatron import in dumper plugin
- [Tracing] Report the quick_finish stage before the trace context is aborted
- [DSV4.1][FIX] DP-attention idle/padded crashes in engram hasher and low-ratio compress
- deepep_v2: validate Qwen4-Exp (Qwen3.8-Flash-Next) for --moe-a2a-backend deepep_v2
- [NPU] [DOC] Add Ascend NPU (A3) deployment scenario to Qwen3.8 cookbook
- [Bugfix][DSV4.1] Skip FlashMLA sched precompute when decoding_sched_meta exceeds 48KiB smem
- 4*5090 run nvidia/Qwen3.8-Flash-Next-NVFP4
- [DCP] Restore GLM-5.3 Flash target-only decode CP
- Docs
- Python not yet supported