feat(modules): Add profiling motivation sections to optimization modules

Browse Source

- Quantization: Shows FP32 memory usage, motivates precision reduction
- Compression: Shows weight distribution, motivates pruning
- Acceleration: Shows CNN compute bottleneck, motivates vectorization

Each module now follows pattern: Profile → Discover → Fix

...

This commit is contained in:

Vijay Janapa Reddi

2025-11-09 12:26:03 -05:00

parent 976f0ed278

commit ef1a5ec7fd

3 changed files with 0 additions and 4509 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

1189

modules/source/16_acceleration/acceleration_dev.py

File diff suppressed because it is too large Load Diff

1776

modules/source/17_quantization/quantization_dev.py

File diff suppressed because it is too large Load Diff

1544

modules/source/18_compression/compression_dev.py

File diff suppressed because it is too large Load Diff