Vijay Janapa Reddi caca0e3903 Fix Module 16 quantization syntax and imports ...

Fix misplaced triple-quote causing syntax error and add Sequential import

2025-11-10 07:30:40 -05:00

..

01_tensor

…

02_activations

…

03_layers

…

04_losses

…

05_autograd

…

06_optimizers

Fix Module 06 optimizers: Use duck typing for Tensor validation and extract grad data properly in AdamW

2025-11-10 07:26:07 -05:00

07_training

…

08_dataloader

…

09_spatial

…

10_tokenization

…

11_embeddings

…

12_attention

Fix Module 12 attention: Correct masking logic to use 0 for masked positions instead of negative values

2025-11-10 07:26:09 -05:00

13_transformers

…

14_profiling

Remove internal restructuring documentation

2025-11-09 17:03:43 -05:00

15_memoization

Fix Module 15 memoization: Add optional mask parameter to MockTransformerBlock forward method

2025-11-10 07:26:11 -05:00

16_quantization

Fix Module 16 quantization syntax and imports

2025-11-10 07:30:40 -05:00

17_compression

Update release documentation and advanced modules

2025-11-09 16:51:55 -05:00

18_acceleration

docs: add comprehensive docstrings to optimization modules 16-19

2025-11-09 14:38:44 -05:00

19_benchmarking

Update release documentation and advanced modules

2025-11-09 16:51:55 -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