CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : remove unused constants

Browse Source
This commit is contained in:
Georgi Gerganov
2025-10-22 15:46:31 +03:00
parent 60599b1645
commit 8af562e83e
1 changed files with 0 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
ggml/src/ggml-metal/ggml-metal.metal
View File

@@ -8127,17 +8127,6 @@ kernel void kernel_set_rows_f(
constant bool FC_mul_mm_bc_inp [[function_constant(FC_MUL_MM + 0)]];
constant bool FC_mul_mm_bc_out [[function_constant(FC_MUL_MM + 1)]];
#define BLOCK_SIZE_M 64 // 8 simdgroup matrices from matrix A
#define BLOCK_SIZE_N 32 // 4 simdgroup matrices from matrix B
#define BLOCK_SIZE_K 32
#define THREAD_MAT_M 4 // each thread take 4 simdgroup matrices from matrix A
#define THREAD_MAT_N 2 // each thread take 2 simdgroup matrices from matrix B
#define THREAD_PER_BLOCK 128
#define THREAD_PER_ROW 2 // 2 thread for each row in matrix A to load numbers
#define THREAD_PER_COL 4 // 4 thread for each row in matrix B to load numbers
#define SG_MAT_SIZE 64 // simdgroup matrix is of shape 8x8
#define SG_MAT_ROW 8
// each block_q contains 16*nl weights
template<typename S0, typename S0_4x4, typename S0_8x8, typename S1, typename S1_2x4, typename S1_8x8, typename block_q, short nl, void (*dequantize_func)(device const block_q *, short, thread S0_4x4 &), typename T0, typename T0_4x4, typename T1, typename T1_2x4>
kernel void kernel_mul_mm(