Commit History

vulkan: support fattn sinks (llama/15126)
d7e9115

jeffbolznv commited on

vulkan: Handle updated FA dim2/3 definition (llama/14518)
d1e619e

jeffbolznv commited on

vulkan: support mixed/deepseekR1 FA head sizes (llama/14509)
90cefa0

jeffbolznv commited on

vulkan: support softmax/FA batch and broadcast (llama/14449)
f6b0b76

jeffbolznv commited on

vulkan: move common FA code to flash_attn_base.comp (llama/13556)
ad8b504

jeffbolznv commited on

vulkan: workaround FA compile failures on macos (llama/13517)
06833bc

jeffbolznv commited on

vulkan: scalar flash attention implementation (llama/13324)
3331abd

jeffbolznv commited on