From 154e0d75fccf1784fe9ff6fd76a630b66563da3d Mon Sep 17 00:00:00 2001 From: Kawrakow <48489457+ikawrakow@users.noreply.github.com> Date: Sat, 27 Jul 2024 07:55:01 +0200 Subject: Merge mainline llama.cpp (#3) * Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow --- ggml/src/ggml-cann/kernels/ascendc_kernels.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 ggml/src/ggml-cann/kernels/ascendc_kernels.h (limited to 'ggml/src/ggml-cann/kernels/ascendc_kernels.h') diff --git a/ggml/src/ggml-cann/kernels/ascendc_kernels.h b/ggml/src/ggml-cann/kernels/ascendc_kernels.h new file mode 100644 index 00000000..bf891475 --- /dev/null +++ b/ggml/src/ggml-cann/kernels/ascendc_kernels.h @@ -0,0 +1,17 @@ +#ifndef ASCENDC_KERNELS_H +#define ASCENDC_KERNELS_H + +#include "aclrtlaunch_ascendc_get_row_f32.h" +#include "aclrtlaunch_ascendc_get_row_f16.h" +#include "aclrtlaunch_ascendc_get_row_q8_0.h" +#include "aclrtlaunch_ascendc_get_row_q4_0.h" + +#include "aclrtlaunch_ascendc_quantize_f32_q8_0.h" +#include "aclrtlaunch_ascendc_quantize_f16_q8_0.h" + +#include "aclrtlaunch_ascendc_dup_by_rows_fp16.h" +#include "aclrtlaunch_ascendc_dup_by_rows_fp32.h" +#include "aclrtlaunch_ascendc_dup_by_rows_fp32_to_fp16.h" +#include "aclrtlaunch_ascendc_dup_by_rows_fp16_to_fp32.h" + +#endif // ASCENDC_KERNELS_H -- cgit v1.2.3