From b369aaa23f5860f3fc6f77e7c74a32f1b2e5553c Mon Sep 17 00:00:00 2001 From: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com> Date: Tue, 30 Dec 2025 23:38:46 +0800 Subject: [PATCH] [Diffusion] Refine diffusion profling doc (#16163) Co-authored-by: github-actions[bot] --- python/sglang/multimodal_gen/docs/profiling.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/python/sglang/multimodal_gen/docs/profiling.md b/python/sglang/multimodal_gen/docs/profiling.md index cf7ddc215..b445138c0 100644 --- a/python/sglang/multimodal_gen/docs/profiling.md +++ b/python/sglang/multimodal_gen/docs/profiling.md @@ -130,3 +130,7 @@ nsys profile \ - **Reduce trace size**: Use `--num-profiled-timesteps` with smaller values or `--delay`/`--duration` with Nsight Systems - **Stage-specific analysis**: Use `--profile` alone for denoising stage, add `--profile-all-stages` for full pipeline - **Multiple runs**: Profile with different prompts and resolutions to identify bottlenecks across workloads + +## FAQ + +- If you are profiling `sglang generate` with Nsight Systems and find that the generated profiler file did not capture any CUDA kernels, you can resolve this issue by increasing the model's inference steps to extend the execution time.