trending/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-10-27 07:14:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add automatic direct convolution selection (#2134)

Browse Source
This commit is contained in:
leejet
2026-10-13 23:25:19 +08:00
committed by GitHub
parent d763dae3b8
commit 46362fc4c0
15 changed files with 259 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/pipeline/diffusion_engine.cpp
+54
View File
@@ -18,6 +18,7 @@
#include "core/ggml_runner.h"
#include "core/ggml_tensor_utils.h"
#include "core/layer_split_partition.h"
#include "core/probe/conv_direct.h"
#include "core/probe/flash_attn.h"
#include "model.h"
@@ -951,7 +952,15 @@ bool StableDiffusionGGML::init(const sd_ctx_params_t* sd_ctx_params) {
LOG_ERROR("invalid flash_attn_mode '%s': %s", flash_mode.c_str(), flash_error.c_str());
return false;
}
const std::string conv_mode = SAFE_STR(sd_ctx_params->conv_direct_mode);
std::string conv_error;
if (!sd_parse_conv_direct_assignment(conv_mode, &conv_direct_assignment, &conv_error)) {
LOG_ERROR("invalid conv_direct_mode '%s': %s", conv_mode.c_str(), conv_error.c_str());
return false;
}
flash_attn_by_backend.clear();
conv2d_direct_by_backend.clear();
conv3d_direct_by_backend.clear();
conditioning_cache_->set_capacity(static_cast<size_t>(sd_ctx_params->conditioning_cache_size));
auto configuration = std::make_unique<ModelConfig>(*sd_ctx_params);
n_threads = sd_ctx_params->n_threads;
@@ -1224,6 +1233,34 @@ bool StableDiffusionGGML::flash_attention_for(SDBackendModule module) {
return enabled;
}
bool StableDiffusionGGML::conv_direct_for(SDBackendModule module, bool conv3d) {
const auto& params = config_->params;
const std::string mode = conv_direct_assignment.get(module);
if (mode == "on" || mode == "off") {
return mode == "on";
}
if (strlen(SAFE_STR(params.conv_direct_mode)) == 0 &&
(module == SDBackendModule::VAE ? params.vae_conv_direct : params.diffusion_conv_direct)) {
return true;
}
auto& by_backend = conv3d ? conv3d_direct_by_backend : conv2d_direct_by_backend;
auto backends = backend_manager.runtime_backends(module);
bool enabled = !backends.empty();
bool any_enabled = false;
for (auto backend : backends) {
auto it = by_backend.find(backend);
if (it == by_backend.end()) {
it = by_backend.emplace(backend, sd_probe_conv_direct(backend, conv3d)).first;
}
enabled = enabled && it->second;
any_enabled = any_enabled || it->second;
}
if (any_enabled && !enabled) {
LOG_INFO("conv%dd direct auto: %s -> off (compute devices disagree)", conv3d ? 3 : 2, sd_backend_module_name(module));
}
return enabled;
}
bool StableDiffusionGGML::validate_and_load_runners() {
const auto* sd_ctx_params = &config_->params;
const bool use_tae = uses_tae();
@@ -1261,6 +1298,23 @@ bool StableDiffusionGGML::validate_and_load_runners() {
if (sd_ctx_params->sage_attn && !set_sage_attention_enabled(true)) {
return false;
}
const auto set_conv_direct = [this](SDBackendModule module, const std::vector<GGMLRunner*>& runners) {
const bool conv2d = conv_direct_for(module, false);
const bool conv3d = conv_direct_for(module, true);
for (auto runner : runners) {
if (runner != nullptr) {
runner->set_conv2d_direct_enabled(conv2d);
runner->set_conv3d_direct_enabled(conv3d);
}
}
};
set_conv_direct(SDBackendModule::DIFFUSION, {diffusion_model.get(), high_noise_diffusion_model.get()});
if (first_stage_model || preview_vae || audio_vae_model) {
set_conv_direct(SDBackendModule::VAE, {first_stage_model.get(), preview_vae.get(), audio_vae_model.get()});
}
if (control_net) {
set_conv_direct(SDBackendModule::CONTROL_NET, {control_net.get()});
}
LOG_VERBOSE("validating model metadata");
std::set<std::string> ignore_tensors;