Vijay Janapa Reddi 34a8d04791 feat(modules): Add profiling motivation sections to optimization modules ...

- 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

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

..

01_tensor

fix(module-01): Fix batched matmul and transpose grad preservation

2025-10-27 20:28:53 -04:00

02_activations

fix(module-02): Rewrite Softmax to use Tensor operations

2025-10-27 20:29:35 -04:00

03_layers

fix(module-03): Rewrite Dropout to use Tensor operations

2025-10-27 20:29:43 -04:00

04_losses

feat: Add Milestone 04 (CNN Revolution 1998) + Clean spatial imports

2025-09-30 17:04:41 -04:00

05_autograd

Merge transformer-training into dev

2025-10-30 17:48:11 -04:00

06_optimizers

feat: Add Milestone 04 (CNN Revolution 1998) + Clean spatial imports

2025-09-30 17:04:41 -04:00

07_training

feat(autograd): Fix gradient flow through all transformer components

2025-10-30 10:20:33 -04:00

08_dataloader

🤖 Fix transformer module exports and milestone 05 imports

2025-10-27 16:17:55 -04:00

09_spatial

feat: Add Milestone 04 (CNN Revolution 1998) + Clean spatial imports

2025-09-30 17:04:41 -04:00

10_tokenization

Merge transformer-training into dev

2025-10-30 17:48:11 -04:00

11_embeddings

feat: Add PyTorch-style __call__ methods and update milestone syntax

2025-10-28 13:46:05 -04:00

12_attention

feat(autograd): Fix gradient flow through all transformer components

2025-10-30 10:20:33 -04:00

13_transformers

Merge transformer-training into dev

2025-10-30 17:48:11 -04:00

14_kvcaching

feat(memoization): Add profiling motivation section

2025-11-09 09:16:08 -05:00

15_profiling

feat(profiler): Add helper functions for optimization modules

2025-11-09 09:15:13 -05:00

16_acceleration

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

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

17_quantization

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

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

18_compression

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

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

19_benchmarking

Add normalized scoring and MLPerf principles to Module 19

2025-11-07 20:04:46 -05:00

20_capstone

Implement MLPerf Edu Competition module (Module 20)

2025-11-07 20:04:57 -05:00

20_competition

Implement MLPerf Edu Competition module (Module 20)

2025-11-07 20:04:57 -05:00