kanshan/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-04 10:10:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : fix mat-vec Q8_0 kernel for BS > 1

Browse Source
This commit is contained in:
Georgi Gerganov
2023-12-31 12:26:21 +02:00
parent 6435a3de31
commit ad7cf37fe8
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml-metal.metal
+7
View File
@@ -1071,8 +1071,15 @@ kernel void kernel_mul_mv_q8_0_f32(
constant int64_t & ne00,
constant int64_t & ne01,
constant int64_t & ne02,
constant uint64_t & nb00,
constant uint64_t & nb01,
constant uint64_t & nb02,
constant int64_t & ne10,
constant int64_t & ne11,
constant int64_t & ne12,
constant uint64_t & nb10,
constant uint64_t & nb11,
constant uint64_t & nb12,
constant int64_t & ne0,
constant int64_t & ne1,
constant uint & r2 [[buffer(17)]],