From 7a32fcb3b29f4db8aed8a85dc58eb958fb118153 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Tue, 25 Apr 2023 23:40:51 +0300 Subject: ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179) * ggml : add Q8_0 quantization format (rename the old one to Q8_1) * tests : fix test-quantize-fns * ggml : finalize Q8_0 implementation * ggml : use q4_0_q8_0 and q4_2_q8_0 * ggml : fix Q8_0 dot product bug (ARM) * ggml : Q8_0 unroll x2 * ggml : fix bug - using wrong block type * ggml : extend quantize_fns_t with "vec_dot_type" * ggml : fix Q8_0 to use 255 values out of 256 * ggml : fix assert using wrong QK4_2 instead of QK4_3 --- ggml-cuda.h | 1 + 1 file changed, 1 insertion(+) (limited to 'ggml-cuda.h') diff --git a/ggml-cuda.h b/ggml-cuda.h index 370bbc75..4048ea49 100644 --- a/ggml-cuda.h +++ b/ggml-cuda.h @@ -35,6 +35,7 @@ void dequantize_row_q4_0_cuda(const void * vx, float * y, int k, cudaStream_t st void dequantize_row_q4_1_cuda(const void * vx, float * y, int k, cudaStream_t stream); void dequantize_row_q4_2_cuda(const void * vx, float * y, int k, cudaStream_t stream); void dequantize_row_q4_3_cuda(const void * vx, float * y, int k, cudaStream_t stream); +void dequantize_row_q8_0_cuda(const void * vx, float * y, int k, cudaStream_t stream); #ifdef __cplusplus } -- cgit v1.2.3