Skip to content

optimize FlashAttention kernel #74

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
LeeWant wants to merge 1 commit into
base: main
Choose a base branch
from
Open

optimize FlashAttention kernel #74

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 1 addition & 3 deletions src/myvllm/layers/attention.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,11 +156,9 @@ def flash_attention_varlen_kernel(
m_i = tl.zeros([BLOCK_M], dtype=tl.float32) - 1e10
acc = tl.zeros([BLOCK_M, head_dim], dtype=tl.float32)

# Number of blocks to process
num_blocks = tl.cdiv(seq_len, BLOCK_N)

# Loop over K, V blocks
for block_n in range(num_blocks):
for block_n in range(start_m + 1):
start_n = block_n * BLOCK_N
offs_n = start_n + tl.arange(0, BLOCK_N)

Expand Down