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

ggml: add ops for WAN video model (cuda && cpu) (#15669)

Browse Source 
* add conv3d support

* add ggml_pad_ext for cpu & cuda backend

* cuda/cpu: add im2col_3d support

* cuda: make im2col a little faster

* fix cuda pad/scale/im2col3d

* make im2col_3d faster

* gguf: support loading tensors which n_dims > GGML_MAX_DIMS

* fix cuda get_rows

* avoid ggml_conv_3d conflict

* correct GGML_OP_COUNT assertion

* avoid build failure

* avoid build failure on MacOS

* cuda: remove unnecessary MIN define

* fix cpu im2col_3d

* adjust the code style

* cuda: use simpler loop in get_rows

* add test_im2col_3d to test-backend-ops

* test-backend-ops.cpp: remove trailing whitespace

* cpu: im2col_3d support non continuous src

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>

* fix test_im2col_3d

* remove unused variables

* cuda: get_rows: dfloat2 -> float2

* add test_pad_ext to test-backend-ops.cpp

* add gguf_init_from_file_ext impl

* Revert "gguf: support loading tensors which n_dims > GGML_MAX_DIMS"

This reverts commit d8377a0a37.

* Revert "add gguf_init_from_file_ext impl"

This reverts commit d9f1d13208.

* update ggml_backend_vk_device_supports_op

* fix ggml_backend_vk_device_supports_op

* update other backend supports op for ggml_pad_ext

* metal/opencl/sycl/vulkan: fix GGML_OP_PAD check in supports_op

---------

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
This commit is contained in:
leejet
2025-09-04 16:38:49 +08:00
committed by GitHub
parent 5421f63ab0
commit 0a1b3982cd
17 changed files with 759 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
ggml/include/ggml.h
View File

@@ -511,6 +511,7 @@ extern "C" {
GGML_OP_CONV_TRANSPOSE_1D,
GGML_OP_IM2COL,
GGML_OP_IM2COL_BACK,
GGML_OP_IM2COL_3D,
GGML_OP_CONV_2D,
GGML_OP_CONV_3D,
GGML_OP_CONV_2D_DW,
@@ -1870,6 +1871,41 @@ extern "C" {
int d0, // dilation dimension 0
int d1); // dilation dimension 1
GGML_API struct ggml_tensor * ggml_im2col_3d(
struct ggml_context * ctx,
struct ggml_tensor * a,
struct ggml_tensor * b,
int64_t IC,
int s0, // stride width
int s1, // stride height
int s2, // stride depth
int p0, // padding width
int p1, // padding height
int p2, // padding depth
int d0, // dilation width
int d1, // dilation height
int d2, // dilation depth
enum ggml_type dst_type);
// a: [OC*IC, KD, KH, KW]
// b: [N*IC, ID, IH, IW]
// result: [N*OC, OD, OH, OW]
GGML_API struct ggml_tensor * ggml_conv_3d(
struct ggml_context * ctx,
struct ggml_tensor * a,
struct ggml_tensor * b,
int64_t IC,
int s0, // stride width
int s1, // stride height
int s2, // stride depth
int p0, // padding width
int p1, // padding height
int p2, // padding depth
int d0, // dilation width
int d1, // dilation height
int d2 // dilation depth
);
// kernel size is a->ne[0] x a->ne[1]
// stride is equal to kernel size
// padding is zero
@@ -1941,7 +1977,7 @@ extern "C" {
int d0, // dilation dimension 0
int d1); // dilation dimension 1
GGML_API struct ggml_tensor * ggml_conv_3d(
GGML_API struct ggml_tensor * ggml_conv_3d_direct(
struct ggml_context * ctx,
struct ggml_tensor * a, // kernel [KW, KH, KD, IC * OC]
struct ggml_tensor * b, // input [W, H, D, C * N]
@@ -2048,6 +2084,19 @@ extern "C" {
int p2,
int p3);
GGML_API struct ggml_tensor * ggml_pad_ext(
struct ggml_context * ctx,
struct ggml_tensor * a,
int lp0,
int rp0,
int lp1,
int rp1,
int lp2,
int rp2,
int lp3,
int rp3
);
// pad each dimension with reflection: [a, b, c, d] -> [b, a, b, c, d, c]
GGML_API struct ggml_tensor * ggml_pad_reflect_1d(
struct ggml_context * ctx,