tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-20 01:27:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

opencl: split ggml-opencl.cl into multiple files and cleanup (#12886)

Browse Source 
* opencl: refactor - split the kernel files

---------

Co-authored-by: Shangqing Gu <quic_shawngu@quicinc.com>

* opencl: split more kernels into separate files

* opencl: specify subgroup size instead of querying it

* opencl: refine Adreno cl compiler version parsing

* opencl: skip some kernels not used by Adreno on old compilers

* opencl: refine logic for selecting Adreno kernels

* opencl: refine Adreno cl compiler version

* opencl: cleanup preprocessor for kernels

* opencl: consider Adreno CL compiler on Windows

* opencl: add final newline for `mul_mv_f16_f16.cl`

---------

Co-authored-by: Shangqing Gu <quic_shawngu@quicinc.com>
This commit is contained in:
lhez
2025-04-15 12:26:00 -07:00
committed by GitHub
parent f8f820cc4d
commit 80f19b4186
43 changed files with 5021 additions and 4996 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
ggml/src/ggml-opencl/CMakeLists.txt
View File

@ -54,16 +54,41 @@ function(ggml_opencl_add_kernel KNAME)
endfunction()
set(GGML_OPENCL_KERNELS
ggml-opencl
ggml-opencl_mm
ggml-opencl_cvt
ggml-opencl_gemv_noshuffle
ggml-opencl_gemv_noshuffle_general
ggml-opencl_mul_mat_Ab_Bi_8x4
ggml-opencl_transpose_16
ggml-opencl_transpose_32
ggml-opencl_transpose_32_16
ggml-opencl_im2col
add
clamp
cpy
cvt
diag_mask_inf
gelu
gemv_noshuffle_general
gemv_noshuffle
get_rows
im2col_f32
im2col_f16
mul_mat_Ab_Bi_8x4
mul_mv_f16_f16
mul_mv_f16_f32_1row
mul_mv_f16_f32_l4
mul_mv_f16_f32
mul_mv_f32_f32
mul_mv_q4_0_f32
mul_mv_q4_0_f32_v
mul_mv_q4_0_f32_8x_flat
mul_mv_q4_0_f32_1d_8x_flat
mul_mv_q4_0_f32_1d_16x_flat
mul_mv_q6_k
mul
norm
relu
rms_norm
rope
scale
silu
softmax_4_f32
softmax_4_f16
softmax_f32
softmax_f16
transpose
)
foreach (K ${GGML_OPENCL_KERNELS})