issues
search
microsoft
/
nnfusion
A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.
MIT License
937
stars
157
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
upgrade hlsl profile, aligning with tuner
#482
mzmssg
closed
1 year ago
0
op validation
#481
mzmssg
closed
1 year ago
0
Zimiao/load onnx rawdata
#480
mzmssg
closed
1 year ago
0
Wenxh/xbox onnx test
#479
wenxcs
closed
1 year ago
0
Convert Boolean to int16
#478
mzmssg
closed
1 year ago
0
Xbox support op check: Abs Acos Add And ArgMax ArgMin
#477
LeiWang1999
closed
1 year ago
0
Wenxh/xbox onnx test
#476
wenxcs
closed
1 year ago
0
add version 15 support of operator Shape and unit test
#475
donglinb
closed
1 year ago
1
Run ONNX Backend standard test for NNFusion
#474
wenxcs
closed
1 year ago
0
Yuqxia/validateop
#473
xiayuqing0622
closed
1 year ago
0
Refactor onnx tensor loading
#472
mzmssg
closed
1 year ago
1
Support const folding with Antares CPU kernel
#471
xysmlx
closed
1 year ago
0
Run ONNX Backend standard test for NNFusion
#470
wenxcs
closed
1 year ago
0
[BUG] "More than one instance of overloaded function" for half type
#469
mzmssg
closed
1 year ago
1
[BUG] int64_t datatype issue
#468
LeiWang1999
closed
1 year ago
0
Update operators and fix external memory bug
#467
jlxue
closed
1 year ago
0
Merge latest fix
#466
mzmssg
closed
1 year ago
0
Workflow
#465
donglinb
opened
1 year ago
0
[BUG] Cuda built-in kernels
#464
wxthu
opened
1 year ago
0
[BUG]msg: CUDA driver version is insufficient for CUDA runtime version
#463
wxthu
opened
1 year ago
2
Will NNfusion be supported on Ubuntu20.04 and Cuda 11 and Pytorch
#462
wxthu
opened
1 year ago
0
Generated para_info.json will have symbol for input tensors' shape
#461
wenxcs
closed
1 year ago
1
Fix ONNX debug script
#460
xysmlx
closed
1 year ago
0
Cuda support
#459
wenxcs
closed
1 year ago
1
Add interface for multi-graph
#458
wenxcs
closed
1 year ago
4
[BUG]
#457
idreamerhx
opened
1 year ago
3
Add new multi graph codegen feature
#456
wenxcs
closed
1 year ago
12
Use check-spelling/check-spelling@v0.0.20
#455
jsoref
closed
1 year ago
0
Support allocate hlsl tensor
#454
mzmssg
closed
1 year ago
3
OPT model: Fix Where and ScatterND bugs; Free host memory after copying to device for HLSL
#453
jlxue
opened
1 year ago
10
[BUG] NNFusion may eliminate results in training
#452
xysmlx
opened
1 year ago
0
Support Conv3D ONNX frontend and AntaresIR; Format code style
#451
xysmlx
opened
2 years ago
2
[BUG] does not support nvidia A30
#450
zhaohb
opened
2 years ago
2
[Fix] support variable steps' slice operation of antares ir
#449
LeiWang1999
closed
2 years ago
0
[Fix] nnfusion jit inference fix
#448
LeiWang1999
closed
2 years ago
0
[BUG] improper return datatype of `get_workspace_size`
#447
LeiWang1999
closed
1 year ago
0
[BUG] nnfusion jit data type mismatch with float16 precision
#446
LeiWang1999
opened
2 years ago
0
[BUG] gpt2-model cuda codegen failed.
#445
LeiWang1999
opened
2 years ago
0
[Feat] accelerate fp16 inference with cudnn library
#444
LeiWang1999
closed
2 years ago
0
[ENHANCEMENT] Suggest to insert nvtx Range into cuda generated code.
#443
LeiWang1999
opened
2 years ago
0
Question about rKernels
#442
ArmageddonKnight
closed
2 years ago
1
[BUG] Compile lstm.onnx failed.
#441
LeiWang1999
opened
2 years ago
1
Fix some hlsl kernel launch problem;
#440
wenxcs
closed
2 years ago
0
Remove double config;
#439
wenxcs
closed
2 years ago
0
Add more Antares info for HLSL customized kernel
#438
wenxcs
closed
2 years ago
0
Fix bert fp16 codegen
#437
LeiWang1999
closed
2 years ago
2
[BUG] incorrect codegen for bert-fp16.onnx
#436
LeiWang1999
opened
2 years ago
0
Fix translate pad op && batchnormal layer fp16 codegen
#435
LeiWang1999
closed
2 years ago
1
[BUG] build cuda_codegen of densenet161-fp16.onnx failed
#434
LeiWang1999
opened
2 years ago
1
[Fix/Feat] Correct the fp16 inference of resnet50.onnx
#433
LeiWang1999
closed
1 year ago
0
Previous
Next