Skill rating

Compact SGLang torch-profiler triage skill. Use when Codex should inspect an existing `trace.json(.gz)` or profile directory, trigger `sglang.profiler` against a live server, and return one compact re

Run SGLang auto benchmark searches with tiered server-flag sweeps, canonical dataset preparation, ShareGPT auto-download, custom-data conversion/validation, SLA or fixed-QPS benchmarking, CSV export,

Use when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.

Use when adding a new diffusion model or Diffusers pipeline to SGLang.

Generate an e2e profiling trace of an SGLang server run. Launches a server, validates accuracy, captures a Chrome-compatible trace, and returns the profile path.

Step-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks)

Use when optimizing an existing SGLang diffusion kernel with AKO4ALL, including AKO4ALL repo hygiene, custom microbench setup, ncu-guided iteration, and end-to-end denoise validation. Also use when a

Guide to SGLang CI workflow orchestration — stage ordering, fast-fail, gating, partitioning, execution modes, and debugging CI failures. Use when modifying CI workflows, adding stages, debugging CI pi

Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.

Guide for writing SGLang CI/UT tests. Covers CustomTestCase, CI registration, server fixtures, model selection, mock testing, and test placement. Always read test/README.md for the full CI layout, how

Use when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion.

Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang's jit_kernel module