Changyeon Kim 8f275a7c45 ggml: Add POOL2D OP for GPU acceleration to the Vulkan backend in the MobileVLM model. (#9763) 1 rok pred
..
CMakeLists.txt db20f50cf4 cmake : Link vulkan-shaders-gen with pthreads (#8835) 1 rok pred
acc.comp 2f3c1466ff llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model. (#8984) 1 rok pred
add.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
argsort.comp 544f409b4b vulkan : argsort barriers must be under uniform control flow (ggml/951) 1 rok pred
clamp.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
concat.comp 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 rok pred
copy.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
cos.comp 231cff5f6f sync : ggml 1 rok pred
dequant_f32.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
dequant_funcs.comp 751fcfc6c3 Vulkan IQ4_NL Support (#8613) 1 rok pred
dequant_head.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
dequant_iq4_nl.comp 751fcfc6c3 Vulkan IQ4_NL Support (#8613) 1 rok pred
dequant_q2_k.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
dequant_q3_k.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
dequant_q4_0.comp 751fcfc6c3 Vulkan IQ4_NL Support (#8613) 1 rok pred
dequant_q4_1.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
dequant_q4_k.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
dequant_q5_0.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
dequant_q5_1.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
dequant_q5_k.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
dequant_q6_k.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
dequant_q8_0.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
diag_mask_inf.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
div.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
gelu.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
gelu_quick.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
generic_binary_head.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
generic_head.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
generic_unary_head.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
get_rows.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
get_rows_quant.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
group_norm.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
im2col.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
leaky_relu.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
mul.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
mul_mat_split_k_reduce.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
mul_mat_vec.comp 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 rok pred
mul_mat_vec_base.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
mul_mat_vec_nc.comp 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 rok pred
mul_mat_vec_p021.comp 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 rok pred
mul_mat_vec_q2_k.comp 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 rok pred
mul_mat_vec_q3_k.comp 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 rok pred
mul_mat_vec_q4_k.comp 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 rok pred
mul_mat_vec_q5_k.comp 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 rok pred
mul_mat_vec_q6_k.comp 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 rok pred
mul_mm.comp 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 rok pred
norm.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
pad.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
pool2d.comp 8f275a7c45 ggml: Add POOL2D OP for GPU acceleration to the Vulkan backend in the MobileVLM model. (#9763) 1 rok pred
relu.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
repeat.comp 5fd89a70ea Vulkan Optimizations and Fixes (#8959) 1 rok pred
rms_norm.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
rope_head.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
rope_neox.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
rope_norm.comp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 rok pred
scale.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
silu.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
sin.comp 231cff5f6f sync : ggml 1 rok pred
soft_max.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
square.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
sum_rows.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
tanh.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
timestep_embedding.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
types.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
upscale.comp a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904) 1 rok pred
vulkan-shaders-gen.cpp 8f275a7c45 ggml: Add POOL2D OP for GPU acceleration to the Vulkan backend in the MobileVLM model. (#9763) 1 rok pred