Merge nucleic/sleek-ember-seal-uady into dev

This commit is contained in:
2026-07-30 21:39:52 -07:00
parent 40176d0c76
commit a374fa40b6
3 changed files with 72 additions and 10 deletions
+4 -2
View File
@@ -234,8 +234,10 @@ ml/purpose-classifier/venv/bin/python ml/purpose-classifier/quantize_coreml.py \
--overwrite-output
```
Activation calibration is grouped to keep temporary Core ML packages bounded and prints
progress while it runs. The candidate uses per-tensor asymmetric uint8 activations,
Activation calibration writes its temporary packages under the candidate output directory
and removes each package immediately after prediction; this avoids Core ML Tools retaining
one full weight copy per calibration step until process exit. It prints progress while it
runs. The candidate uses per-tensor asymmetric uint8 activations,
per-channel symmetric int8 linear weights, and per-tensor asymmetric uint8 embedding
weights. It fails the command if the resulting package exceeds 25 MiB.