gaspersic/triton
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[DOCS] Correct spelling (#665)

Browse Source 
This PR corrects spelling like #664 for Triton-MLIR. It should not break anything.
This commit is contained in:
Shintaro Iwasaki
2022-09-16 15:07:34 -07:00
committed by GitHub
parent e9e1a4e682
commit 13669b46a6
13 changed files with 21 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/tutorials/02-fused-softmax.py
View File

@@ -78,7 +78,7 @@ def softmax_kernel(
input_ptrs = row_start_ptr + col_offsets
# Load the row into SRAM, using a mask since BLOCK_SIZE may be > than n_cols
row = tl.load(input_ptrs, mask=col_offsets < n_cols, other=-float('inf'))
# Substract maximum for numerical stability
# Subtract maximum for numerical stability
row_minus_max = row - tl.max(row, axis=0)
# Note that exponentials in Triton are fast but approximate (i.e., think __expf in CUDA)
numerator = tl.exp(row_minus_max)