vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-13 07:29:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

improve the computing buffer estimate

Browse source
This commit is contained in:
Zonghang Li 2025-06-19 08:02:43 +00:00
parent 0b4ffdfde5
commit dd589561b4
8 changed files with 87 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

16
common/profiler.h
View file

@ -293,10 +293,20 @@ struct model_bytes {
int64_t nb_layer;
int64_t nb_output;
// used to estimate the compute buffer size
int64_t nb_output_w;
int64_t nb_attn_norm_w;
int64_t nb_ffn_gate_w;
int64_t nb_ffn_down_w;
model_bytes() :
nb_input (0),
nb_layer (0),
nb_output(0) {}
nb_input (0),
nb_layer (0),
nb_output (0),
nb_output_w (0),
nb_attn_norm_w(0),
nb_ffn_gate_w (0),
nb_ffn_down_w (0) {}
};
struct disk_props {