Implement the AO API in torchchat quantization handlers and unify log… #3195

Job	Run time
gather-models-cpu	9s
test-tinystories-executorch (16-core-ubuntu)	17m 50s
torchchat-command-load-test (macos-14)	1m 29s
test-tinystories-executorch (macos-14-xlarge)	15m 49s
test-gguf-util (macos-14)	4m 31s
test-mps (macos-m1-stable)	1m 21s
test-mps-dtype (macos-m1-stable)	1m 52s
compile-gguf (macos-14)	4m 18s
gather-models-gpu	12s
runner-aoti (16-core-ubuntu)	5m 7s
runner-et (16-core-ubuntu)	7m 38s
test-torchao-experimental (macos-14-xlarge)	8m 31s
runner-et (macos-14-xlarge)	7m 33s
runner-aoti (macos-14-xlarge)	3m 3s
test-build-runner-et-android / linux-job	11m 8s
test-cpu-aoti (x86_64, stories15M)	16m 52s
test-cpu-compile (x86_64, stories15M)	16m 6s
test-cpu-eval-sanity-check-float16 (x86_64, stories15M)	29m 8s
test-cpu-eval-sanity-check (x86_64, stories15M)	9m 22s
test-cpu-aoti (aarch64, stories15M)	10m 3s
test-cpu-compile (aarch64, stories15M)	8m 56s
test-cpu-eval-sanity-check-float16 (aarch64, stories15M)	6m 21s
test-cpu-eval-sanity-check (aarch64, stories15M)	8m 55s
test-cpu-eval-sanity-check-float32 (x86_64, stories15M)	37m 36s
test-cpu-eval-sanity-check-float32 (aarch64, stories15M)	7m 40s
test-gpu-aoti-float16 (cuda, stories15M) / linux-job	11m 44s
test-gpu-compile (cuda, stories15M) / linux-job	22m 54s
test-gpu-aoti-float32 (cuda, stories15M) / linux-job	11m 50s
test-gpu-aoti-bfloat16 (cuda, stories15M) / linux-job	12m 46s
test-gpu-eval-sanity-check (cuda, stories15M) / linux-job	11m 32s
	5h 12m 16s

Provide feedback