upstream-archive/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-10-03 11:27:43 -05:00
Code Issues Packages Projects Releases Wiki Activity

refactor: centralize circular RoPE and extend image model support (#2039)

Browse Source
This commit is contained in:
leejet
2026-09-24 01:45:14 +08:00
committed by GitHub
parent 500ef5fa7c
commit 88411ef1e0
17 changed files with 611 additions and 564 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/model/diffusion/anima.hpp
+35 -32
View File
@@ -603,34 +603,37 @@ namespace Anima {
return std::pow(extrapolation_ratio, static_cast<float>(axis_dim) / static_cast<float>(axis_dim - 2));
}
static std::vector<float> gen_anima_image_pe_vec(int bs,
int h,
int w,
int patch_size,
int theta,
const std::vector<int>& axes_dim,
float h_extrapolation_ratio,
float w_extrapolation_ratio,
float t_extrapolation_ratio,
const std::vector<ggml_tensor*>& ref_latents) {
auto ids = Rope::gen_flux_ids(h,
w,
patch_size,
bs,
static_cast<int>(axes_dim.size()),
0,
{},
ref_latents,
Rope::RefIndexMode::FIXED,
1.0f,
false);
static Rope::Embedding gen_anima_image_pe_vec(int bs,
int h,
int w,
int patch_size,
int theta,
const std::vector<int>& axes_dim,
float h_extrapolation_ratio,
float w_extrapolation_ratio,
float t_extrapolation_ratio,
const std::vector<ggml_tensor*>& ref_latents) {
Rope::Embedding result;
result.batch_size = bs;
result.ids = Rope::gen_flux_ids(h,
w,
patch_size,
bs,
static_cast<int>(axes_dim.size()),
0,
{},
ref_latents,
Rope::RefIndexMode::FIXED,
1.0f,
false, &result.positions);
std::vector<float> axis_thetas = {
static_cast<float>(theta) * calc_ntk_factor(t_extrapolation_ratio, axes_dim[0]),
static_cast<float>(theta) * calc_ntk_factor(h_extrapolation_ratio, axes_dim[1]),
static_cast<float>(theta) * calc_ntk_factor(w_extrapolation_ratio, axes_dim[2]),
};
return Rope::embed_nd(ids, bs, axis_thetas, axes_dim);
result.values = Rope::embed_nd(result.ids, bs, axis_thetas, axes_dim, result.layout, &result.frequencies);
return result;
}
ggml_cgraph* build_graph(const sd::Tensor<float>& x_tensor,
@@ -657,16 +660,16 @@ namespace Anima {
int64_t h_pad = x->ne[1] + pad_h;
int64_t w_pad = x->ne[0] + pad_w;
image_pe_vec = gen_anima_image_pe_vec(1,
static_cast<int>(h_pad),
static_cast<int>(w_pad),
static_cast<int>(config.patch_size),
config.theta,
config.axes_dim,
4.0f,
4.0f,
1.0f,
ref_latents);
image_pe_vec = finish_rope_pe(gen_anima_image_pe_vec(1,
static_cast<int>(h_pad),
static_cast<int>(w_pad),
static_cast<int>(config.patch_size),
config.theta,
config.axes_dim,
4.0f,
4.0f,
1.0f,
ref_latents));
int64_t image_pos_len = static_cast<int64_t>(image_pe_vec.size()) / (2 * 2 * (config.head_dim / 2));
auto image_pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, 2, 2, config.head_dim / 2, image_pos_len);
set_backend_tensor_data(image_pe, image_pe_vec.data());
src/model/diffusion/boogu.hpp
+24 -18
View File
@@ -720,15 +720,18 @@ namespace Boogu {
}
}
__STATIC_INLINE__ std::vector<float> gen_boogu_pe(int h,
int w,
int patch_size,
int bs,
int context_len,
const std::vector<ggml_tensor*>& ref_latents,
int theta,
const std::vector<int>& axes_dim) {
std::vector<std::vector<float>> ids;
__STATIC_INLINE__ Rope::Embedding gen_boogu_pe(int h,
int w,
int patch_size,
int bs,
int context_len,
const std::vector<ggml_tensor*>& ref_latents,
int theta,
const std::vector<int>& axes_dim) {
Rope::Embedding result;
result.batch_size = bs;
result.positions.append_tokens(context_len);
auto& ids = result.ids;
ids.reserve(static_cast<size_t>(bs) * context_len);
for (int b = 0; b < bs; b++) {
for (int i = 0; i < context_len; i++) {
@@ -741,15 +744,18 @@ namespace Boogu {
for (ggml_tensor* ref : ref_latents) {
int ref_h_tokens = patched_token_count(ref->ne[1], patch_size);
int ref_w_tokens = patched_token_count(ref->ne[0], patch_size);
result.positions.append_image(ref_h_tokens, ref_w_tokens);
append_spatial_ids(ids, bs, pe_shift, ref_h_tokens, ref_w_tokens);
pe_shift += std::max(ref_h_tokens, ref_w_tokens);
}
int h_tokens = patched_token_count(h, patch_size);
int w_tokens = patched_token_count(w, patch_size);
result.positions.append_image(h_tokens, w_tokens);
append_spatial_ids(ids, bs, pe_shift, h_tokens, w_tokens);
return Rope::embed_nd(ids, bs, static_cast<float>(theta), axes_dim);
result.values = Rope::embed_nd(ids, bs, static_cast<float>(theta), axes_dim, result.layout, &result.frequencies);
return result;
}
struct BooguImageRunner : public DiffusionModelRunner {
@@ -793,14 +799,14 @@ namespace Boogu {
ref_latents.push_back(make_input(ref_latent_tensor));
}
pe_vec = gen_boogu_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
ref_latents,
config.theta,
config.axes_dim);
pe_vec = finish_rope_pe(gen_boogu_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
ref_latents,
config.theta,
config.axes_dim));
int pos_len = static_cast<int>(pe_vec.size() / config.axes_dim_sum / 2);
auto pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, 2, 2, config.axes_dim_sum / 2, pos_len);
set_backend_tensor_data(pe, pe_vec.data());
src/model/diffusion/ernie_image.hpp
+7 -9
View File
@@ -415,15 +415,13 @@ namespace ErnieImage {
GGML_ASSERT(!context_tensor.empty());
ggml_tensor* context = make_input(context_tensor);
pe_vec = Rope::gen_ernie_image_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
config.theta,
circular_y_enabled,
circular_x_enabled,
config.axes_dim);
pe_vec = finish_rope_pe(Rope::gen_ernie_image_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
config.theta,
config.axes_dim));
int pos_len = static_cast<int>(pe_vec.size() / config.axes_dim_sum / 2);
auto pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, config.axes_dim_sum, 1, pos_len, 2);
set_backend_tensor_data(pe, pe_vec.data());
src/model/diffusion/flux.hpp
+12 -14
View File
@@ -1548,20 +1548,18 @@ namespace Flux {
} else if (version == VERSION_OVIS_IMAGE) {
txt_arange_dims = {1, 2};
}
pe_vec = Rope::gen_flux_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
txt_arange_dims,
ref_latents,
ref_index_mode,
config.ref_index_scale,
config.theta,
circular_y_enabled,
circular_x_enabled,
config.axes_dim,
sd_version_is_longcat(version));
pe_vec = finish_rope_pe(Rope::gen_flux_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
txt_arange_dims,
ref_latents,
ref_index_mode,
config.ref_index_scale,
config.theta,
config.axes_dim,
sd_version_is_longcat(version)));
int pos_len = static_cast<int>(pe_vec.size() / config.axes_dim_sum / 2);
// LOG_VERBOSE("pos_len %d", pos_len);
auto pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, 2, 2, config.axes_dim_sum / 2, pos_len);
src/model/diffusion/ideogram4.hpp
+28 -43
View File
@@ -149,18 +149,21 @@ namespace Ideogram4 {
return std::make_shared<Linear>(in_features, out_features, bias);
}
__STATIC_INLINE__ std::vector<float> gen_ideogram4_pe(int grid_h,
int grid_w,
int bs,
int context_len,
int head_dim,
int rope_theta,
const std::vector<int>& mrope_section,
bool circular_x = false,
bool circular_y = false) {
__STATIC_INLINE__ Rope::Embedding gen_ideogram4_pe(int grid_h,
int grid_w,
int bs,
int context_len,
int head_dim,
int rope_theta,
const std::vector<int>& mrope_section) {
GGML_ASSERT(bs == 1);
std::vector<std::vector<float>> ids(static_cast<size_t>(bs) * (context_len + grid_h * grid_w),
std::vector<float>(3, 0.f));
Rope::Embedding result;
result.batch_size = bs;
result.positions.append_tokens(context_len);
result.positions.append_image(grid_h, grid_w);
result.ids.assign(static_cast<size_t>(bs) * (context_len + grid_h * grid_w),
std::vector<float>(3, 0.f));
auto& ids = result.ids;
for (int i = 0; i < context_len; ++i) {
ids[i] = {static_cast<float>(i), static_cast<float>(i), static_cast<float>(i)};
@@ -175,29 +178,13 @@ namespace Ideogram4 {
}
}
std::vector<std::vector<int>> axis_wrap_dims(3);
if (circular_y || circular_x) {
size_t total_len = static_cast<size_t>(bs) * (context_len + grid_h * grid_w);
axis_wrap_dims[1].assign(total_len, 0);
axis_wrap_dims[2].assign(total_len, 0);
if (circular_y) {
for (size_t idx = static_cast<size_t>(context_len); idx < total_len; ++idx) {
axis_wrap_dims[1][idx] = grid_h;
}
}
if (circular_x) {
for (size_t idx = static_cast<size_t>(context_len); idx < total_len; ++idx) {
axis_wrap_dims[2][idx] = grid_w;
}
}
}
return Rope::embed_interleaved_mrope(ids,
bs,
static_cast<float>(rope_theta),
head_dim,
mrope_section,
axis_wrap_dims);
result.values = Rope::embed_interleaved_mrope(ids,
bs,
static_cast<float>(rope_theta),
head_dim,
mrope_section,
&result.frequencies);
return result;
}
class Ideogram4Attention : public GGMLBlock {
@@ -509,15 +496,13 @@ namespace Ideogram4 {
int64_t head_dim = config.emb_dim / config.num_heads;
auto runner_ctx = get_context();
pe_vec = gen_ideogram4_pe(static_cast<int>(grid_h),
static_cast<int>(grid_w),
static_cast<int>(x->ne[3]),
static_cast<int>(context_len),
static_cast<int>(head_dim),
static_cast<int>(config.rope_theta),
config.mrope_section,
runner_ctx.circular_x_enabled,
runner_ctx.circular_y_enabled);
pe_vec = finish_rope_pe(gen_ideogram4_pe(static_cast<int>(grid_h),
static_cast<int>(grid_w),
static_cast<int>(x->ne[3]),
static_cast<int>(context_len),
static_cast<int>(head_dim),
static_cast<int>(config.rope_theta),
config.mrope_section));
auto pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, 2, 2, head_dim / 2, pos_len);
set_backend_tensor_data(pe, pe_vec.data());
src/model/diffusion/krea2.hpp
+26 -21
View File
@@ -689,23 +689,28 @@ namespace Krea2 {
}
};
__STATIC_INLINE__ std::vector<float> gen_krea2_pe(int h,
int w,
int patch_size,
int bs,
int context_len,
float theta,
const std::vector<int>& axes_dim,
const std::vector<ggml_tensor*>& ref_latents,
Rope::RefIndexMode ref_index_mode) {
__STATIC_INLINE__ Rope::Embedding gen_krea2_pe(int h,
int w,
int patch_size,
int bs,
int context_len,
float theta,
const std::vector<int>& axes_dim,
const std::vector<ggml_tensor*>& ref_latents,
Rope::RefIndexMode ref_index_mode) {
Rope::Embedding result;
result.batch_size = bs;
result.positions.append_tokens(context_len);
auto txt_ids = Rope::gen_flux_txt_ids(bs, context_len, 3, {});
auto img_ids = Rope::gen_flux_img_ids(h, w, patch_size, bs, 3, 0, 0, 0, false);
auto img_ids = Rope::gen_flux_img_ids(h, w, patch_size, bs, 3, 0, 0, 0, false, &result.positions);
auto ids = Rope::concat_ids(txt_ids, img_ids, bs);
if (ref_latents.size() > 0) {
auto refs_ids = Rope::gen_refs_ids(patch_size, bs, 3, 1, ref_latents, ref_index_mode, 1.0f, false, 0);
auto refs_ids = Rope::gen_refs_ids(patch_size, bs, 3, 1, ref_latents, ref_index_mode, 1.0f, false, 0, &result.positions);
ids = Rope::concat_ids(ids, refs_ids, bs);
}
return Rope::embed_nd(ids, bs, theta, axes_dim);
result.ids = std::move(ids);
result.values = Rope::embed_nd(result.ids, bs, theta, axes_dim, result.layout, &result.frequencies);
return result;
}
struct Krea2Runner : public DiffusionModelRunner {
@@ -749,15 +754,15 @@ namespace Krea2 {
ref_latents.push_back(make_input(ref_latent_tensor));
}
pe_vec = gen_krea2_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
config.theta,
config.axes_dim,
ref_latents,
ref_image_params.ref_index_mode);
pe_vec = finish_rope_pe(gen_krea2_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
config.theta,
config.axes_dim,
ref_latents,
ref_image_params.ref_index_mode));
int pos_len = static_cast<int>(pe_vec.size() / config.axes_dim_sum / 2);
auto pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, 2, 2, config.axes_dim_sum / 2, pos_len);
set_backend_tensor_data(pe, pe_vec.data());
src/model/diffusion/lens.hpp
+6 -8
View File
@@ -384,14 +384,12 @@ namespace Lens {
GGML_ASSERT(!context_tensor.empty());
ggml_tensor* context = make_input(context_tensor);
pe_vec = Rope::gen_lens_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
config.theta,
circular_y_enabled,
circular_x_enabled,
config.axes_dim);
pe_vec = finish_rope_pe(Rope::gen_lens_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
config.theta,
config.axes_dim));
int pos_len = static_cast<int>(pe_vec.size() / config.axes_dim_sum / 2);
auto pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, 2, 2, config.axes_dim_sum / 2, pos_len);
set_backend_tensor_data(pe, pe_vec.data());
src/model/diffusion/llada_image.hpp
+16 -18
View File
@@ -412,16 +412,14 @@ namespace LLaDAImage {
GGML_ASSERT(!context_tensor.empty());
ggml_tensor* context = make_input(context_tensor);
pe_vec = Rope::gen_llada_image_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
ZImage::SEQ_MULTI_OF,
config.theta,
circular_y_enabled,
circular_x_enabled,
config.axes_dim);
pe_vec = finish_rope_pe(Rope::gen_llada_image_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
ZImage::SEQ_MULTI_OF,
config.theta,
config.axes_dim));
int pos_len = static_cast<int>(pe_vec.size() / config.axes_dim_sum / 2);
auto pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, 2, 2, config.axes_dim_sum / 2, pos_len);
set_backend_tensor_data(pe, pe_vec.data());
@@ -461,14 +459,14 @@ namespace LLaDAImage {
ggml_tensor* source = make_input(source_tensor);
GGML_ASSERT(x->ne[3] == 1);
pe_vec = Rope::gen_llada_image_edit_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(context->ne[1]),
semantic != nullptr ? static_cast<int>(semantic->ne[1]) : 0,
ZImage::SEQ_MULTI_OF,
config.theta,
config.axes_dim);
pe_vec = finish_rope_pe(Rope::gen_llada_image_edit_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(context->ne[1]),
semantic != nullptr ? static_cast<int>(semantic->ne[1]) : 0,
ZImage::SEQ_MULTI_OF,
config.theta,
config.axes_dim));
int pos_len = static_cast<int>(pe_vec.size() / config.axes_dim_sum / 2);
auto pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, 2, 2, config.axes_dim_sum / 2, pos_len);
set_backend_tensor_data(pe, pe_vec.data());
src/model/diffusion/mage_flow.hpp
+7 -7
View File
@@ -110,13 +110,13 @@ namespace MageFlow {
}
int batch_size = static_cast<int>(x->ne[3]);
pe_vec = Rope::gen_mage_flow_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
batch_size,
static_cast<int>(context->ne[1]),
ref_latents,
config.theta,
config.axes_dim);
pe_vec = finish_rope_pe(Rope::gen_mage_flow_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
batch_size,
static_cast<int>(context->ne[1]),
ref_latents,
config.theta,
config.axes_dim));
int pos_len = static_cast<int>(pe_vec.size() / config.axes_dim_sum / 2);
auto pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, 2, 2, config.axes_dim_sum / 2, pos_len);
set_backend_tensor_data(pe, pe_vec.data());
src/model/diffusion/minit2i.hpp
+18 -3
View File
@@ -154,18 +154,26 @@ namespace MiniT2I {
return Rope::flatten(Rope::rope(Rope::linspace(0.f, static_cast<float>(length - 1), length), head_dim, 10000.f));
}
inline std::vector<float> make_vision_rope(int side, int head_dim) {
inline Rope::Embedding make_vision_rope(int side, int head_dim) {
GGML_ASSERT(head_dim % 4 == 0);
int dim = head_dim / 2;
int quarter = dim / 2;
int length = side * side;
Rope::Embedding result;
result.positions.append_image(side, side);
std::vector<float> out(static_cast<size_t>(length) * (head_dim / 2) * 4);
std::vector<float> freqs(quarter);
for (int i = 0; i < quarter; ++i) {
freqs[i] = 1.0f / std::pow(10000.0f, static_cast<float>(2 * i) / static_cast<float>(dim));
}
for (int axis : {1, 2}) {
for (float frequency : freqs) {
result.frequencies.push_back({static_cast<size_t>(axis), frequency});
}
}
for (int y = 0; y < side; ++y) {
for (int x = 0; x < side; ++x) {
result.ids.push_back({0.f, static_cast<float>(y), static_cast<float>(x)});
int pos = y * side + x;
size_t base = static_cast<size_t>(pos) * (head_dim / 2) * 4;
for (int i = 0; i < quarter; ++i) {
@@ -182,7 +190,8 @@ namespace MiniT2I {
}
}
}
return out;
result.values = std::move(out);
return result;
}
struct SwiGLUMlp : public GGMLBlock {
@@ -475,6 +484,8 @@ namespace MiniT2I {
int64_t cached_txt_len = -1;
int64_t cached_hidden_size = -1;
int64_t cached_head_dim = -1;
bool cached_circular_x = false;
bool cached_circular_y = false;
MiniT2IRunner(ggml_backend_t backend,
const String2TensorStorage& tensor_storage_map = {},
@@ -521,6 +532,8 @@ namespace MiniT2I {
cached_txt_len == txt_len &&
cached_hidden_size == config.hidden_size &&
cached_head_dim == config.head_dim &&
cached_circular_x == circular_x_enabled &&
cached_circular_y == circular_y_enabled &&
cached_pos_embed != nullptr &&
cached_txt_pe != nullptr &&
cached_joint_pe != nullptr) {
@@ -531,7 +544,7 @@ namespace MiniT2I {
auto pos_embed_vec = make_2d_sincos_pos_embed(static_cast<int>(img_side), static_cast<int>(config.hidden_size));
auto txt_pe_vec = make_text_rope(static_cast<int>(txt_len), static_cast<int>(config.head_dim));
auto img_pe_vec = make_vision_rope(static_cast<int>(img_side), static_cast<int>(config.head_dim));
auto img_pe_vec = finish_rope_pe(make_vision_rope(static_cast<int>(img_side), static_cast<int>(config.head_dim)));
auto joint_pe_vec = txt_pe_vec;
joint_pe_vec.insert(joint_pe_vec.end(), img_pe_vec.begin(), img_pe_vec.end());
@@ -561,6 +574,8 @@ namespace MiniT2I {
cached_txt_len = txt_len;
cached_hidden_size = config.hidden_size;
cached_head_dim = config.head_dim;
cached_circular_x = circular_x_enabled;
cached_circular_y = circular_y_enabled;
}
ggml_cgraph* build_graph(const sd::Tensor<float>& x_tensor,
src/model/diffusion/model.hpp
+6 -1
View File
@@ -7,7 +7,7 @@
#include "core/ggml_runner.h"
#include "core/tensor_ggml.hpp"
#include "model/common/rope.hpp"
#include "model/common/rope_circular.hpp"
#include "model_manager.h"
enum class RefImageResizeMode {
@@ -184,6 +184,11 @@ struct DiffusionModelRunner : public GGMLRunner {
protected:
std::string prefix;
std::vector<float> finish_rope_pe(Rope::Embedding embedding) {
Rope::apply_circular(embedding, circular_x_enabled, circular_y_enabled);
return std::move(embedding.values);
}
public:
DiffusionModelRunner(ggml_backend_t backend,
const std::string& prefix,
src/model/diffusion/pid.hpp
+21 -21
View File
@@ -135,13 +135,13 @@ namespace Pid {
return Rope::flatten(Rope::rope(Rope::linspace(0.f, static_cast<float>(length - 1), length), dim, theta));
}
inline std::vector<float> make_rope_2d(int height,
int width,
int dim,
float theta = 10000.f,
float scale = 16.f,
int ref_grid_h = 0,
int ref_grid_w = 0) {
inline Rope::Embedding make_rope_2d(int height,
int width,
int dim,
float theta = 10000.f,
float scale = 16.f,
int ref_grid_h = 0,
int ref_grid_w = 0) {
GGML_ASSERT(dim % 4 == 0);
return Rope::embed_2d_interleaved(height, width, dim, theta, scale, ref_grid_h, ref_grid_w);
}
@@ -867,13 +867,13 @@ namespace Pid {
int64_t Hs = Hp / config.patch_size;
int64_t Ws = Wp / config.patch_size;
pos_img_vec = make_rope_2d(static_cast<int>(Hs),
static_cast<int>(Ws),
static_cast<int>(config.hidden_size / config.num_groups),
10000.f,
16.f,
static_cast<int>(config.rope_ref_grid_h),
static_cast<int>(config.rope_ref_grid_w));
pos_img_vec = finish_rope_pe(make_rope_2d(static_cast<int>(Hs),
static_cast<int>(Ws),
static_cast<int>(config.hidden_size / config.num_groups),
10000.f,
16.f,
static_cast<int>(config.rope_ref_grid_h),
static_cast<int>(config.rope_ref_grid_w)));
auto pos_img = ggml_new_tensor_4d(compute_ctx,
GGML_TYPE_F32,
2,
@@ -904,13 +904,13 @@ namespace Pid {
1);
set_backend_tensor_data(pixel_pos, pixel_pos_vec.data());
pixel_pos_comp_vec = make_rope_2d(static_cast<int>(Hs),
static_cast<int>(Ws),
static_cast<int>(config.pixel_attn_hidden_size / config.pixel_num_groups),
10000.f,
16.f,
static_cast<int>(config.rope_ref_grid_h),
static_cast<int>(config.rope_ref_grid_w));
pixel_pos_comp_vec = finish_rope_pe(make_rope_2d(static_cast<int>(Hs),
static_cast<int>(Ws),
static_cast<int>(config.pixel_attn_hidden_size / config.pixel_num_groups),
10000.f,
16.f,
static_cast<int>(config.rope_ref_grid_h),
static_cast<int>(config.rope_ref_grid_w)));
auto pixel_pos_comp = ggml_new_tensor_4d(compute_ctx,
GGML_TYPE_F32,
2,
src/model/diffusion/qwen_image.hpp
+10 -12
View File
@@ -635,18 +635,16 @@ namespace Qwen {
ref_index_mode = Rope::RefIndexMode::DECREASE;
}
pe_vec = Rope::gen_qwen_image_pe(time_len,
static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
batch_size,
static_cast<int>(context->ne[1]),
ref_latents,
ref_index_mode,
config.theta,
circular_y_enabled,
circular_x_enabled,
config.axes_dim);
pe_vec = finish_rope_pe(Rope::gen_qwen_image_pe(time_len,
static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
batch_size,
static_cast<int>(context->ne[1]),
ref_latents,
ref_index_mode,
config.theta,
config.axes_dim));
int pos_len = static_cast<int>(pe_vec.size() / config.axes_dim_sum / 2);
// LOG_VERBOSE("pos_len %d", pos_len);
auto pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, 2, 2, config.axes_dim_sum / 2, pos_len);
src/model/diffusion/qwen_image_2_1.hpp
+17 -2
View File
@@ -68,6 +68,7 @@ namespace Qwen {
std::vector<QwenImage21Segment> segments;
std::vector<std::vector<float>> positions;
int64_t prefix_length = 0;
Rope::PositionLayout rope_layout;
static QwenImage21Layout build(int64_t text_length,
const sd::Tensor<int32_t>& image_slots,
@@ -82,6 +83,7 @@ namespace Qwen {
auto [height, width] = image_shapes[index];
int64_t start = static_cast<int64_t>(layout.positions.size());
layout.segments.push_back({start, start + height * width, context_start, index});
layout.rope_layout.append_image(static_cast<int>(height), static_cast<int>(width));
for (int64_t h = 0; h < height; ++h) {
for (int64_t w = 0; w < width; ++w) {
layout.positions.push_back({static_cast<float>(position),
@@ -106,6 +108,7 @@ namespace Qwen {
} else {
int64_t start = static_cast<int64_t>(layout.positions.size());
layout.segments.push_back({start, start + i - begin, begin, -1});
layout.rope_layout.append_tokens(i - begin);
for (int64_t j = begin; j < i; ++j, ++position) {
float p = static_cast<float>(position);
layout.positions.push_back({p, p, p});
@@ -418,14 +421,26 @@ namespace Qwen {
}
QwenImage21PrefixCache cache;
if (prefix_cache_enabled && !prefix_cache_disabled && extra != nullptr && extra->prefix_id != 0 && layout.prefix_length > 0) {
cache.name = "qwen_image_2_1.prefix." + std::to_string(extra->prefix_id);
cache.name = "qwen_image_2_1.prefix." + std::to_string(extra->prefix_id) +
".circular." + std::to_string(circular_x_enabled) + std::to_string(circular_y_enabled);
cache.prefix_length = layout.prefix_length;
cache.mode = has_prefix_cache(cache) ? QwenImage21PrefixCache::Mode::REUSE : QwenImage21PrefixCache::Mode::STORE;
}
auto run = [&](const QwenImage21PrefixCache& active_cache) {
const bool cached = active_cache.mode == QwenImage21PrefixCache::Mode::REUSE;
const auto first_position = layout.positions.begin() + (cached ? layout.prefix_length : 0);
pe_data = Rope::embed_nd(std::vector<std::vector<float>>(first_position, layout.positions.end()), 1, 10000.f, config.axes_dim);
Rope::Embedding embedding;
embedding.ids.assign(first_position, layout.positions.end());
const size_t offset = cached ? static_cast<size_t>(layout.prefix_length) : 0;
embedding.positions.token_count = embedding.ids.size();
for (auto region : layout.rope_layout.images) {
if (region.begin >= offset) {
region.begin -= offset;
embedding.positions.images.push_back(region);
}
}
embedding.values = Rope::embed_nd(embedding.ids, 1, 10000.f, config.axes_dim, embedding.layout, &embedding.frequencies);
pe_data = finish_rope_pe(std::move(embedding));
mask_data.clear();
if (!cached) {
for (const auto& segment : layout.segments) {
src/model/diffusion/z_image.hpp
+10 -12
View File
@@ -642,18 +642,16 @@ namespace ZImage {
ref_latents.push_back(make_input(ref_latent_tensor));
}
pe_vec = Rope::gen_z_image_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
SEQ_MULTI_OF,
ref_latents,
ref_index_mode,
config.theta,
circular_y_enabled,
circular_x_enabled,
config.axes_dim);
pe_vec = finish_rope_pe(Rope::gen_z_image_pe(static_cast<int>(x->ne[1]),
static_cast<int>(x->ne[0]),
config.patch_size,
static_cast<int>(x->ne[3]),
static_cast<int>(context->ne[1]),
SEQ_MULTI_OF,
ref_latents,
ref_index_mode,
config.theta,
config.axes_dim));
int pos_len = static_cast<int>(pe_vec.size() / config.axes_dim_sum / 2);
// LOG_VERBOSE("pos_len %d", pos_len);
auto pe = ggml_new_tensor_4d(compute_ctx, GGML_TYPE_F32, 2, 2, config.axes_dim_sum / 2, pos_len);