Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions 20241217_st.md
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,7 @@ There are a few layers of abstraction in the shapetracker API, let's start from
```python
from tinygrad.shape.view import View

# The two by two matrix is represneted as shape being (2, 2), strides being (2, 1)
# The two by two matrix is represented as shape being (2, 2), strides being (2, 1)
a = View.create(shape=(2, 2), strides=(2, 1))

# In order to get the "strategy" we talked about (row * 2 + col), we call a special method:
Expand Down Expand Up @@ -110,7 +110,7 @@ it actually translates to the readable render output:

The outer most node is an addition, this is the + sign.
The first child is yet another addition, it adds a zero const, and a multiplication. We can deduce that the zero is some
artifacts that's not shown. THe multiplication multiplies two things:
artifacts that's not shown. The multiplication multiplies two things:
the first is a range, ranging from zero to three. This is the ridx0.
the second is a const, value is 2.

Expand Down