mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-06 00:34:35 +00:00
This commit is contained in:
parent
fd7d5e870d
commit
909cfd498c
@ -2857,7 +2857,6 @@ kernel void kernel_flash_attn_ext_vec_f16(
|
||||
// O = diag(ms)*O
|
||||
#pragma unroll
|
||||
for (short ii = 0; ii < D4; ii += NW) {
|
||||
const short i = ii + tiisg;
|
||||
lo[ii/NW] *= ms;
|
||||
}
|
||||
}
|
||||
|
Loading…
Reference in New Issue
Block a user