nihui
/
ncnn
Not watched
1
0
Fork 0
Code
Releases 46 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
2942 Commits
5 Branches
354 MB
2 Download
 
 
 
 
 
 
Tree: 1d6bfdca38
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '1d6bfdca38'
${ noResults }
ncnn/tools/pnnx/src
nihui 1d6bfdca38
fix pnnx pass on fp16 weight, common fp16 conversion routines (#4743) 		3 years ago
..
pass_level0 pnnx fuse transformer clip attention and diffusers attentionblock (#4727) 3 years ago
pass_level1 pnnx convert torch std (#4715) 3 years ago
pass_level2 pnnx convert sdpa (#4722) 3 years ago
pass_level3 fix pnnx pass on fp16 weight, common fp16 conversion routines (#4743) 3 years ago
pass_level4 PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago
pass_level5 fix pnnx pass on fp16 weight, common fp16 conversion routines (#4743) 3 years ago
pass_ncnn fix pnnx pass on fp16 weight, common fp16 conversion routines (#4743) 3 years ago
CMakeLists.txt pnnx convert sdpa (#4722) 3 years ago
ir.cpp fix pnnx pass on fp16 weight, common fp16 conversion routines (#4743) 3 years ago
ir.h fix pnnx pass on fp16 weight, common fp16 conversion routines (#4743) 3 years ago
main.cpp pnnx fuse transformer clip attention and diffusers attentionblock (#4727) 3 years ago
onnx.proto pnnx save onnx zero (#4077) 3 years ago
pass_level0.cpp pnnx flatten input tuple list (#4498) 3 years ago
pass_level0.h save foldable constants in file for reducing memory usage (#4337) 3 years ago
pass_level1.cpp pnnx torch 2.0 (#4579) 3 years ago
pass_level1.h pnnx export weight inside moduleop (#3902) 4 years ago
pass_level2.cpp pnnx fuse multiheadattention (#4544) 3 years ago
pass_level2.h pnnx fuse more function to module (#4351) 3 years ago
pass_level3.cpp pnnx reset maxpool return_indices if only output found, drop convtransposed output_size arg for static output padding (#4654) 3 years ago
pass_level3.h pnnx recognize foldable scalar and fuse it into expression (#4639) 3 years ago
pass_level4.cpp pnnx fold constant (#3521) 4 years ago
pass_level4.h PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago
pass_level5.cpp pnnx fuse multiheadattention (#4544) 3 years ago
pass_level5.h save foldable constants in file for reducing memory usage (#4337) 3 years ago
pass_ncnn.cpp enrich ncnn binary broadcast rules (#4513) 3 years ago
pass_ncnn.h PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago
save_ncnn.cpp pnnx fp16 option for ncnn and onnx weight type (#4350) 3 years ago
save_ncnn.h pnnx fp16 option for ncnn and onnx weight type (#4350) 3 years ago
save_onnx.cpp fix pnnx pass on fp16 weight, common fp16 conversion routines (#4743) 3 years ago
save_onnx.h pnnx fp16 option for ncnn and onnx weight type (#4350) 3 years ago
save_onnx_cxxabi_bridge.cpp pnnx save onnx zero (#4077) 3 years ago
storezip.cpp PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago
storezip.h multiheadattention attn mask (#4668) 3 years ago
utils.cpp fix pnnx pass on fp16 weight, common fp16 conversion routines (#4743) 3 years ago
utils.h fix pnnx pass on fp16 weight, common fp16 conversion routines (#4743) 3 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

No Description

C++ C Python Text Protocol Buffer other