]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
vulkan: support softmax/FA batch and broadcast (llama/14449)
authorJeff Bolz <redacted>
Tue, 1 Jul 2025 08:32:56 +0000 (03:32 -0500)
committerGeorgi Gerganov <redacted>
Sat, 12 Jul 2025 13:05:00 +0000 (16:05 +0300)
commit7e2e170e8c23a9f69a1ce0c2c24ca08695cf8537
treec0cee1328cd029e328f9494a96e81f0bf8276a30
parent175e7719e3d6158e93a93e34fe853070d513c2aa
vulkan: support softmax/FA batch and broadcast (llama/14449)
src/ggml-vulkan/ggml-vulkan.cpp
src/ggml-vulkan/vulkan-shaders/flash_attn.comp
src/ggml-vulkan/vulkan-shaders/flash_attn_base.comp
src/ggml-vulkan/vulkan-shaders/flash_attn_cm1.comp
src/ggml-vulkan/vulkan-shaders/flash_attn_cm2.comp
src/ggml-vulkan/vulkan-shaders/flash_attn_split_k_reduce.comp
src/ggml-vulkan/vulkan-shaders/soft_max.comp