Skip to content

Commit

Permalink
Linter
Browse files Browse the repository at this point in the history
  • Loading branch information
vgokhale committed Jul 8, 2024
1 parent 5e2ffc6 commit 8dd5404
Showing 1 changed file with 1 addition and 4 deletions.
5 changes: 1 addition & 4 deletions python/perf-kernels/flash-attention.py
Original file line number Diff line number Diff line change
Expand Up @@ -319,10 +319,7 @@ def _attn_fwd_inner(acc, l_i, m_i, q, k_ptrs, v_ptrs, bias_ptrs, stride_kn, stri
triton.Config({'BLOCK_M': 16, 'BLOCK_N': 16, 'waves_per_eu': 1, 'PRE_LOAD_V': False}, num_stages=1,
num_warps=4),
],
key=[
'IS_CAUSAL', 'dropout_p', 'MAX_SEQLENS_Q', 'MAX_SEQLENS_K', 'ACTUAL_BLOCK_DMODEL', 'VARLEN',
'HQ', 'HK'
],
key=['IS_CAUSAL', 'dropout_p', 'MAX_SEQLENS_Q', 'MAX_SEQLENS_K', 'ACTUAL_BLOCK_DMODEL', 'VARLEN', 'HQ', 'HK'],
use_cuda_graph=True,
)
@triton.jit
Expand Down

0 comments on commit 8dd5404

Please sign in to comment.