mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-03 09:22:01 +00:00
dc685be466
* CUDA: add FP32 FlashAttention vector kernel * fixup! CUDA: add FP32 FlashAttention vector kernel * fixup! fixup! CUDA: add FP32 FlashAttention vector kernel * fixup! fixup! fixup! CUDA: add FP32 FlashAttention vector kernel
6 lines
213 B
Plaintext
6 lines
213 B
Plaintext
#include "common.cuh"
|
|
|
|
void ggml_cuda_flash_attn_ext_vec_f16(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_flash_attn_ext_vec_f16_no_mma(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|