vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

sync : ggml (#6351)

Browse source 
* sync : ggml

ggml-ci

* cuda : move GGML_CUDA_DMMV constants to dmmv.cuh

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov 2024-03-29 17:45:46 +02:00 • committed by GitHub
parent 069574775c
commit d48ccf3ad4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 25 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

7
ggml-cuda/common.cuh
View file

@ -1,7 +1,8 @@
#pragma once
#include "../ggml.h"
#include "../ggml-cuda.h"
#include "ggml.h"
#include "ggml-cuda.h"
#include <memory>
#if defined(GGML_USE_HIPBLAS)
@ -11,7 +12,7 @@
#define GGML_COMMON_DECL_CUDA
#define GGML_COMMON_IMPL_CUDA
#endif
#include "../ggml-common.h"
#include "ggml-common.h"
#include <cstdio>
#include <array>

8
ggml-cuda/dmmv.cu
View file

@ -2,14 +2,6 @@
#include "dequantize.cuh"
#include "convert.cuh"
// dmmv = dequantize_mul_mat_vec
#ifndef GGML_CUDA_DMMV_X
#define GGML_CUDA_DMMV_X 32
#endif
#ifndef GGML_CUDA_MMV_Y
#define GGML_CUDA_MMV_Y 1
#endif
#ifndef K_QUANTS_PER_ITERATION
#define K_QUANTS_PER_ITERATION 2
#else

11
ggml-cuda/dmmv.cuh
View file

@ -1,5 +1,16 @@
#include "common.cuh"
// dmmv = dequantize_mul_mat_vec
// TODO: remove this?
#ifndef GGML_CUDA_DMMV_X
#define GGML_CUDA_DMMV_X 32
#endif
#ifndef GGML_CUDA_MMV_Y
#define GGML_CUDA_MMV_Y 1
#endif
void ggml_cuda_op_dequantize_mul_mat_vec(
ggml_backend_cuda_context & ctx,
const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, const char * src0_dd_i, const float * src1_ddf_i,