DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-12 03:49:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor: unify runner lifecycles and weight residency (#1940)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-09-06 22:30:45 +08:00
1 parent 6c57cc3b38
commit 462d675018
78 files changed
+2963 -2051
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/model/vae/ltx_vae.hpp
+3 -5
View File
@@ -1334,7 +1334,6 @@ struct LTXVideoVAE : public VAE {
(int)plan.tiles.size());
free_cache_ctx_and_buffer();
cache_tensor_map.clear();
auto output = process_vae_temporal_tiles(input, plan, [&](const sd::Tensor<float>& z_chunk, const VAETemporalTile& tile) {
LOG_DEBUG("LTX VAE temporal tile %lld/%d: latent frames [%lld, %lld), overlap=%d",
@@ -1349,12 +1348,11 @@ struct LTXVideoVAE : public VAE {
static_cast<int>(tile.start),
tile.overlap);
};
return restore_trailing_singleton_dims(GGMLRunner::compute<float>(get_graph, n_threads, true, true, true),
return restore_trailing_singleton_dims(GGMLRunner::compute<float>(get_graph, n_threads, false),
expected_dim);
});
free_cache_ctx_and_buffer();
cache_tensor_map.clear();
return output;
}
@@ -1407,7 +1405,7 @@ struct LTXVideoVAE : public VAE {
auto get_graph = [&]() -> ggml_cgraph* {
return build_graph(input, decode_graph);
};
auto result = restore_trailing_singleton_dims(GGMLRunner::compute<float>(get_graph, n_threads, false, false, false), expected_dim);
auto result = restore_trailing_singleton_dims(GGMLRunner::compute<float>(get_graph, n_threads, false), expected_dim);
if (result.empty()) {
return {};
}
@@ -1420,7 +1418,7 @@ struct LTXVideoVAE : public VAE {
auto get_graph = [&]() -> ggml_cgraph* {
return build_latent_statistics_graph(z, normalize);
};
return restore_trailing_singleton_dims(GGMLRunner::compute<float>(get_graph, n_threads, false, false, false),
return restore_trailing_singleton_dims(GGMLRunner::compute<float>(get_graph, n_threads, false),
static_cast<size_t>(z.dim()));
}