Files
llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_8.cu
Johannes Gäßler 0cf6725e9f CUDA: FA support for Deepseek (Ampere or newer) (#13306)
* CUDA: FA support for Deepseek (Ampere or newer)

* do loop unrolling via C++ template
2025-05-09 13:34:58 +02:00

11 lines
357 B
Plaintext

// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-mma-f16.cuh"
DECL_FATTN_MMA_F16_CASE(64, 64, 8, 8);
DECL_FATTN_MMA_F16_CASE(80, 80, 8, 8);
DECL_FATTN_MMA_F16_CASE(96, 96, 8, 8);
DECL_FATTN_MMA_F16_CASE(112, 112, 8, 8);
DECL_FATTN_MMA_F16_CASE(128, 128, 8, 8);
DECL_FATTN_MMA_F16_CASE(256, 256, 8, 8);