fix: resolve MSVC narrowing conversion warnings (#1969)

This commit is contained in:
leejet
2026-09-13 23:45:54 +08:00
committed by GitHub
parent ca37fad89a
commit 5a5400bf0c
4 changed files with 19 additions and 19 deletions
+1 -1
View File
@@ -146,7 +146,7 @@ namespace SenseNovaU1 {
auto x = ggml_ext_timestep_embedding(ctx->ggml_ctx,
timesteps,
static_cast<int>(frequency_embedding_size),
10000.f,
10000,
1.f);
x = mlp_0->forward(ctx, x);
x = ggml_silu_inplace(ctx->ggml_ctx, x);
+15 -15
View File
@@ -20,22 +20,22 @@ namespace WAN {
constexpr int WAN_GRAPH_SIZE = 10240;
struct WanConfig {
std::string model_type = "t2v";
std::tuple<int, int, int> patch_size = {1, 2, 2};
int64_t text_len = 512;
int64_t in_dim = 16;
int64_t dim = 2048;
int64_t ffn_dim = 8192;
int freq_dim = 256;
int64_t text_dim = 4096;
int64_t out_dim = 16;
int64_t num_heads = 16;
int num_layers = 32;
int vace_layers = 0;
int64_t vace_in_dim = 96;
std::map<int, int> vace_layers_mapping = {};
std::string model_type = "t2v";
std::tuple<int, int, int> patch_size = {1, 2, 2};
int64_t text_len = 512;
int64_t in_dim = 16;
int64_t dim = 2048;
int64_t ffn_dim = 8192;
int freq_dim = 256;
int64_t text_dim = 4096;
int64_t out_dim = 16;
int64_t num_heads = 16;
int num_layers = 32;
int vace_layers = 0;
int64_t vace_in_dim = 96;
std::map<int, int> vace_layers_mapping = {};
int64_t audio_dim = 1024;
int num_audio_token = 4; // excludes the learned padding token
int num_audio_token = 4; // excludes the learned padding token
std::vector<int> audio_inject_layers = {};
std::map<int, int> audio_inject_mapping = {}; // block index -> injector index
std::string adain_mode = "attn_norm";
+1 -1
View File
@@ -564,7 +564,7 @@ public:
int64_t chunk_frames = 5 * decoder->t_upscale;
int64_t pad = (chunk_frames - (num_frames % chunk_frames)) % chunk_frames;
result = ggml_ext_pad_ext(ctx->ggml_ctx, ctx->backend, result, 0, 0, 0, 0, 0, 0, 0, pad, false, false);
result = ggml_ext_pad_ext(ctx->ggml_ctx, ctx->backend, result, 0, 0, 0, 0, 0, 0, 0, static_cast<int>(pad), false, false);
int64_t num_chunks = (num_frames + pad) / chunk_frames;
auto to_trim = decoder->t_upscale - 1;