sglang-diffusion-benchmark-profile

SGLang Diffusion Benchmark and Profile

Use this skill when measuring denoise performance, finding the slow op, checking whether an existing fast path can solve it, or verifying that a hotspot is real before any kernel work in sglang.multimodal_gen.

This skill is diagnosis-first. It owns:

• checked-in denoise benchmark presets
• same-GPU quality/BCG applicability checks with repeated lossless, extra-high, and high rows
• perf dump collection and before/after comparison
• torch.profiler trace capture and quick hotspot ranking
• mapping hot kernels back to known fast paths and fusion families
• packaging confirmed kernel work with enough evidence for the appropriate kernel, Nsight, or framework-specific optimization workflow

This skill does not own low-level kernel authoring or standalone Nsight workflows.

Preflight

Before running any benchmark, profiler, or kernel-validation command:

• use scripts/diffusion_skill_env.py to derive the repo root from sglang.__file__
• verify the repo is writable
• export HF_TOKEN before using gated Hugging Face models such as black-forest-labs/FLUX.*
• export FLASHINFER_DISABLE_VERSION_CHECK=1
• set SGLANG_DIFFUSION_SYNC_STAGE_PROFILING=1 when comparing stage-level denoise/decode timings; the preset helper sets it by default unless the caller explicitly overrides it
• for downloaded checkpoints, use the preset helper's task-owned --model-cache-root together with --cleanup-model-cache; verify the JSONL ledger reports zero residual weight files before moving to the next model
• choose idle GPU(s) before starting perf work; for a comparison matrix, hold the same GPU set and verify it has no foreign process at every run boundary

Native Backend Gate

All diffusion benchmark and profiling results owned by this skill must come from the native SGLang diffusion backend.

Treat any of the following as a hard stop condition:

• Falling back to diffusers backend
• Using diffusers backend
• Loaded diffusers pipeline