CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

sync : ggml (conv ops + cuda MSVC fixes) (#3765)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2023-10-24 21:51:20 +03:00
committed by GitHub
parent abd21fc99f
commit b2f7e04bd3
3 changed files with 369 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
ggml.h
View File

@@ -401,15 +401,16 @@ extern "C" {
GGML_OP_ALIBI,
GGML_OP_CLAMP,
GGML_OP_CONV_1D,
GGML_OP_CONV_2D,
GGML_OP_CONV_1D_STAGE_0, // internal
GGML_OP_CONV_1D_STAGE_1, // internal
GGML_OP_CONV_TRANSPOSE_1D,
GGML_OP_CONV_2D,
GGML_OP_CONV_2D_STAGE_0, // internal
GGML_OP_CONV_2D_STAGE_1, // internal
GGML_OP_CONV_TRANSPOSE_2D,
GGML_OP_POOL_1D,
GGML_OP_POOL_2D,
GGML_OP_CONV_1D_STAGE_0, // internal
GGML_OP_CONV_1D_STAGE_1, // internal
GGML_OP_UPSCALE, // nearest interpolate
GGML_OP_FLASH_ATTN,
@@ -1020,9 +1021,9 @@ extern "C" {
struct ggml_tensor * b,
float eps);
// A: n columns, m rows
// B: n columns, p rows (i.e. we transpose it internally)
// result is m columns, p rows
// A: k columns, n rows => [ne03, ne02, n, k]
// B: k columns, m rows (i.e. we transpose it internally) => [ne03 * x, ne02 * y, m, k]
// result is n columns, m rows => [ne03 * x, ne02 * y, m, n]
GGML_API struct ggml_tensor * ggml_mul_mat(
struct ggml_context * ctx,
struct ggml_tensor * a,