CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-18 11:46:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

sync : ggml (SD ops, tests, kernels) (#4444)

Browse Source 
* sync : ggml (SD ops, tests, kernels)

ggml-ci

* cuda : restore im2col

ggml-ci

* metal : fix accuracy of dequantization kernels

ggml-ci

* cuda : restore correct im2col

ggml-ci

* metal : try to fix moe test by reducing expert size

ggml-ci

* cuda : fix bin bcast when src1 and dst have different types

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov
2023-12-13 21:54:54 +02:00
committed by GitHub
parent 70f806b821
commit 4d98d9a656
6 changed files with 1334 additions and 130 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
ggml.h
View File

@@ -423,7 +423,9 @@ extern "C" {
GGML_OP_POOL_1D,
GGML_OP_POOL_2D,
GGML_OP_UPSCALE, // nearest interpolate
GGML_OP_PAD,
GGML_OP_ARGSORT,
GGML_OP_LEAKY_RELU,
GGML_OP_FLASH_ATTN,
GGML_OP_FLASH_FF,
@@ -463,7 +465,6 @@ extern "C" {
GGML_UNARY_OP_GELU,
GGML_UNARY_OP_GELU_QUICK,
GGML_UNARY_OP_SILU,
GGML_UNARY_OP_LEAKY,
GGML_UNARY_OP_COUNT,
};
@@ -793,6 +794,9 @@ extern "C" {
struct ggml_tensor * a,
struct ggml_tensor * b);
// dst = a
// view(dst, nb1, nb2, nb3, offset) += b
// return dst
GGML_API struct ggml_tensor * ggml_acc(
struct ggml_context * ctx,
struct ggml_tensor * a,
@@ -957,15 +961,14 @@ extern "C" {
struct ggml_context * ctx,
struct ggml_tensor * a);
GGML_API struct ggml_tensor * ggml_leaky(
GGML_API struct ggml_tensor * ggml_leaky_relu(
struct ggml_context * ctx,
struct ggml_tensor * a);
struct ggml_tensor * a, float negative_slope, bool inplace);
GGML_API struct ggml_tensor * ggml_relu_inplace(
struct ggml_context * ctx,
struct ggml_tensor * a);
// TODO: double-check this computation is correct
GGML_API struct ggml_tensor * ggml_gelu(
struct ggml_context * ctx,
struct ggml_tensor * a);
@@ -1551,6 +1554,15 @@ extern "C" {
struct ggml_tensor * a,
int scale_factor);
// pad each dimension with zeros: [x, ..., x] -> [x, ..., x, 0, ..., 0]
GGML_API struct ggml_tensor * ggml_pad(
struct ggml_context * ctx,
struct ggml_tensor * a,
int p0,
int p1,
int p2,
int p3);
// sort rows
enum ggml_sort_order {
GGML_SORT_ASC,