Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp)

03ba2cd verified 27 days ago

150 Bytes

	#include "common.cuh"

	#define CUDA_DIAG_MASK_INF_BLOCK_SIZE 32

	void ggml_cuda_op_diag_mask_inf(ggml_backend_cuda_context & ctx, ggml_tensor * dst);