Home Esplora Aiuto
Accedi
cturan
/
llama.cpp
mirror da https://github.com/cturan/llama.cpp
1
0
Forka 0
File Problemi 0 Wiki
Albero (Tree): 641002fba8
Rami (Branch) Tag
llama.cpp
/
ggml
/
src
/
kompute-shaders
Daniel Bevenius 06943a69f6 ggml : move rope type enum to ggml.h (#8949) 1 anno fa
..
common.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_add.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_addrow.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_cpy_f16_f16.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_cpy_f16_f32.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_cpy_f32_f16.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_cpy_f32_f32.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_diagmask.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_gelu.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_getrows.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_getrows_f16.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_getrows_f32.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_getrows_q4_0.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_getrows_q4_1.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_getrows_q6_k.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_mul.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_mul_mat_f16.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_mul_mat_mat_f32.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_mul_mat_q4_0.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_mul_mat_q4_1.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_mul_mat_q6_k.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_mul_mat_q8_0.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_mul_mv_q_n.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_mul_mv_q_n_pre.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_norm.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_relu.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_rmsnorm.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_rope_f16.comp 06943a69f6 ggml : move rope type enum to ggml.h (#8949) 1 anno fa
op_rope_f32.comp 06943a69f6 ggml : move rope type enum to ggml.h (#8949) 1 anno fa
op_scale.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_scale_8.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_silu.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
op_softmax.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 anno fa
rope_common.comp 06943a69f6 ggml : move rope type enum to ggml.h (#8949) 1 anno fa