github-starred/TinyTorch
2
0
Fork 0
mirror of https://github.com/MLSysBook/TinyTorch.git synced 2026-05-06 12:33:02 -05:00
Code Issues 7 Packages Projects Releases Wiki Activity
Files
4c50ac35fdee1a6092745fdcaf79700159ed664e
TinyTorch/modules
History
Vijay Janapa Reddi 4c50ac35fd Implement pure Tensor with decorator extension pattern 
- Module 01: Pure Tensor class - ZERO gradient code, perfect data structure focus
- Modules 02-04: Clean usage of basic Tensor, no hasattr() hacks anywhere
- Removed Parameter wrapper complexity, use direct Tensor operations
- Each module now focuses ONLY on its core teaching concept
- Prepared elegant decorator pattern for Module 05 autograd extension
- Perfect separation of concerns: data structure → operations → enhancement
2025-09-29 12:15:12 -04:00
..
01_tensor
Implement pure Tensor with decorator extension pattern
2025-09-29 12:15:12 -04:00
02_activations
Clean up activations module: ReLU and Softmax only, remove old dev file
2025-09-28 14:53:43 -04:00
03_layers
Implement pure Tensor with decorator extension pattern
2025-09-29 12:15:12 -04:00
04_losses
Implement pure Tensor with decorator extension pattern
2025-09-29 12:15:12 -04:00
04_networks_backup
Fix module issues and create minimal MNIST training examples
2025-09-29 10:20:33 -04:00
05_autograd
Fix gradient flow with PyTorch-style requires_grad tracking
2025-09-29 10:46:58 -04:00
06_optimizers
Remove old optimizers dev file
2025-09-28 14:54:15 -04:00
07_training
Implement pure Tensor with decorator extension pattern
2025-09-29 12:15:12 -04:00
08_spatial
Clean up spatial module: CNN components with excellent scaling analysis
2025-09-28 14:54:28 -04:00
09_dataloader
Clean up dataloader module: Complete with performance analysis
2025-09-28 14:54:34 -04:00
10_tokenization
Fix tokenization module: Handle emoji test case correctly
2025-09-28 14:54:41 -04:00
11_embeddings
Fix embeddings module: Handle both Tensor and numpy array inputs
2025-09-28 14:54:48 -04:00
12_attention
Fix attention module: Proper causal masking for transformers
2025-09-28 14:54:54 -04:00
13_transformers
Clean up transformers module: Complete transformer architectures
2025-09-28 14:55:01 -04:00
14_profiling
Improve module-developer guidelines and fix all module issues
2025-09-28 09:42:25 -04:00
15_acceleration
Improve module-developer guidelines and fix all module issues
2025-09-28 09:42:25 -04:00
16_quantization
Improve module-developer guidelines and fix all module issues
2025-09-28 09:42:25 -04:00
17_compression
Improve module-developer guidelines and fix all module issues
2025-09-28 09:42:25 -04:00
18_caching
Improve module-developer guidelines and fix all module issues
2025-09-28 09:42:25 -04:00
19_benchmarking
Improve module-developer guidelines and fix all module issues
2025-09-28 09:42:25 -04:00
20_capstone
Fix capstone module: Correct transpose operations for numpy arrays
2025-09-28 14:55:07 -04:00
source
Remove obsolete agent files: Consolidated into new specialized agents
2025-09-28 14:56:15 -04:00