code/scripts
| script | purpose | device |
|---|---|---|
fetch_samples.sh |
downloads the public sample data that is not redistributable (sha256-checked) | no |
bench.py |
stage breakdown of warm frames (pre, host_in, H2D split, sparse / dense trace, b2b, D2H split, post, e2e; p50 / p99; capacity-bucket sweep; checked against the stored CPU reference); --host-only splits the host stages without a device |
yes, via bin/devrun (--host-only: no) |
profile_ops.py |
one eager frame (module / layer signposts) + one traced frame (sparse_<bucket> + dense replays) under the device profiler (python -m tracy -r -p -v ...) |
yes |
profile_summary.py |
the OPT_BASELINE tables from a profile_ops.py ops CSV (per segment, module, layer, op code; top ops; gaps) |
no |
visualizer_report.py |
ttnn-visualizer memory + graph report of one eager frame (never for timing) | yes |
container_smoke.sh |
serve ONE serve profile of the built package (--profile NAME; default profile otherwise), run server/smoke_test.py against it (asserts ETH dispatch, the 12x10 grid and the profile's pins; compares with the stored CPU reference), keep the evidence (container log, /info, the /predict output and the result, in logs/smoke/ of the repo or --log-dir DIR), always stop it; one bin/devrun -t 3600 -k 150 window per profile |
yes |
make_demo.py |
renders media/*.png (BEV / overlay views) from the shipped sample |
yes |
ref_golden.py |
CPU reference (+ ONNX Runtime) goldens for the tests | no |
Everything here ships in code/ on the Hub and inside the image (source.extra_code lists scripts).