Understanding PyTorch Buffers (#288)

rasbt · Jul 26, 2024 · deea13e · deea13e
1 parent 08040f0
commit deea13e
Show file tree

Hide file tree

Showing 4 changed files with 567 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -102,6 +102,7 @@ Several folders contain optional materials as a bonus for interested readers:
   - [Dataloader Intuition with Simple Numbers](ch02/04_bonus_dataloader-intuition)
 - **Chapter 3:**
   - [Comparing Efficient Multi-Head Attention Implementations](ch03/02_bonus_efficient-multihead-attention/mha-implementations.ipynb)
+  - [Understanding PyTorch Buffers](ch03/03_understanding-buffers/understanding-buffers.ipynb)
 - **Chapter 4:**
   - [FLOPS Analysis](ch04/02_performance-analysis/flops-analysis.ipynb)
 - **Chapter 5:**

diff --git a/ch03/03_understanding-buffers/README.md b/ch03/03_understanding-buffers/README.md
@@ -0,0 +1,3 @@
+# Understanding PyTorch Buffers
+
+- [understanding-buffers.ipynb](understanding-buffers.ipynb) explains the idea behind PyTorch buffers, which are used to implement the causal attention mechanism in chapter 3
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,3 @@
		# Understanding PyTorch Buffers

		- [understanding-buffers.ipynb](understanding-buffers.ipynb) explains the idea behind PyTorch buffers, which are used to implement the causal attention mechanism in chapter 3