root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

metal : use F32 prec for K*Q in vec FA (#9595)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-09-23 11:27:47 +03:00 committed by GitHub
parent e62e9789cd
commit bf9c1013ac
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
ggml/src/ggml-metal.metal
View File

@ -2631,11 +2631,11 @@ kernel void kernel_flash_attn_ext_vec_f16(
const short iv3 = iq3 / rv3;
// load the queries from shared memory into local memory
half4 mq[D4];
float4 mq[D4];
for (short ii = 0; ii < D4; ii += NW) {
short i = ii + tiisg;
mq[i] = sq4[i];
mq[i] = (float4) sq4[i];
}
// pointer to the mask
@ -2661,11 +2661,11 @@ kernel void kernel_flash_attn_ext_vec_f16(
for (short ii = 0; ii < D4; ii += NW) {
const short i = ii + tiisg;
half4x4 mk;
mk[0] = pk4[i + 0*(nb11/8)];
mk[1] = pk4[i + 1*(nb11/8)];
mk[2] = pk4[i + 2*(nb11/8)];
mk[3] = pk4[i + 3*(nb11/8)];
float4x4 mk;
mk[0] = (float4) pk4[i + 0*(nb11/8)];
mk[1] = (float4) pk4[i + 1*(nb11/8)];
mk[2] = (float4) pk4[i + 2*(nb11/8)];
mk[3] = (float4) pk4[i + 3*(nb11/8)];
mqk += (float4) (mq[i] * mk);
}