Vijay Janapa ReddiandGitHub 74a2b82cca Merge pull request #1953 from Shashank-Tripathi-07/fix/memoization-cached-generation-missing-self-attention ...

fix(tinytorch): cached generation step excludes current token from self-attention

2026-07-10 23:42:38 +02:00

..

01_tensor

🌐 TinyTorch website update: Release-quality audit for the AI engineering textbook

2026-06-22 17:48:22 +00:00

02_activations

fix(activations): numerically stable sigmoid without overflow warnings

2026-06-21 22:26:57 -04:00

03_layers

fix Dropout to use the module-level seeded rng instead of global np.random (#1869)

2026-06-16 18:58:38 -04:00

04_losses

tinytorch modules clarity (#1738)

2026-05-14 10:24:59 -04:00

05_dataloader

fix(tinytorch): repair release regressions

2026-06-02 13:40:09 -04:00

06_autograd

fix(tinytorch): set requires_grad via attribute in broadcast-gradient test

2026-07-02 18:33:00 +02:00

07_optimizers

fix(tinytorch): single backslashes in SGD diagrams under raw string

2026-06-26 10:36:29 -04:00

08_training

tinytorch modules 07 and 08 diagram fixes

2026-06-26 10:28:00 -04:00

09_convolutions

🌐 TinyTorch website update: Release-quality audit for the AI engineering textbook

2026-06-22 17:48:22 +00:00

10_tokenization

…

11_embeddings

…

12_attention

fix(attention): preserve seq_q and seq_k in MultiHeadAttention mask reshape

2026-06-21 11:32:03 -04:00

13_transformers

fix(tinytorch): fix GPT causal mask convention in module 13

2026-05-18 20:03:05 +05:30

14_profiling

…

15_quantization

fix(quantization): recover constant tensors with |value| > 127

2026-06-21 20:54:20 -04:00

16_compression

…

17_acceleration

…

18_memoization

fix(tinytorch): cached generation step excludes current token from self-attention

2026-07-08 01:43:26 +05:30

19_benchmarking

…

20_capstone

fix(tinytorch): capstone latency divisions crash on coarse timer resolution

2026-07-08 01:48:44 +05:30