anush elangovan
81881a36ea
Fix accidental additions
2022-06-03 06:43:08 +00:00
powderluv
aba351c493
auto detect number of workers.
...
use auto detect for number of pytest workers
2022-06-02 23:32:36 -07:00
anush elangovan
9c70dea957
Pull in TF models
2022-06-03 06:10:24 +00:00
anush elangovan
1fa05fc7c8
Rename to tflite and ignore lit.cfg.py in flake8
2022-06-03 05:21:23 +00:00
yzhang93
16c50cac15
Add the option to use tuned model in shark_runner ( #79 )
2022-06-02 18:25:33 -07:00
anush elangovan
1186d7c58e
disable tflite tests
2022-06-02 20:16:16 +00:00
anush elangovan
8fa5b39bd6
Add importer utils to linux build
2022-06-02 19:33:51 +00:00
anush elangovan
c6ea400178
Fix lit flake8 errors
2022-06-02 18:56:55 +00:00
anush elangovan
395adc2921
Add tflitehub
2022-06-02 16:58:18 +00:00
Stanley Winata
c83ff66a00
Refactor get_iree_module to work with SharkBenchmark ( #82 )
2022-06-01 19:39:15 -07:00
powderluv
0d6c105412
Update README.md
2022-06-01 19:34:05 -07:00
Maksim Levental
4ba3c03c3f
Merge pull request #81 from makslevental/dynamo
...
Dynamo notebook
2022-06-01 21:16:59 -05:00
Ean Garvey
8ad73d365c
Add support for training TF models + fix TF BERT training example ( #80 )
2022-06-01 18:46:07 -07:00
Maksim Levental
c058b39c7c
Merge branch 'nod-ai:main' into dynamo
2022-06-01 20:02:24 -05:00
max
1d2c3ee584
Demo for how dynamo with mlir backend can exist out of (dynamo) tree.
2022-06-01 18:57:58 -05:00
Maksim Levental
05dffd4d59
Demo for how dynamo with mlir backend can exist out of (dynamo) tree. ( #78 )
2022-06-01 14:57:04 -07:00
powderluv
27a33e636d
Update nightly.yml
...
Remove spurious test package
2022-06-01 14:44:39 -07:00
max
4572d2bfba
Demo for how dynamo with mlir backend can exist out of (dynamo) tree.
2022-06-01 15:32:17 -05:00
Stanley Winata
b271daa748
Rectify Vulkan Flags and Command to obtain Vulkan Target Triple ( #77 )
...
-Add correct vulkan flag to run minilm_jit
-Add automatic specification of target triple for better speed.
-Will work when https://github.com/nod-ai/SHARK-Runtime/releases/tag/candidate-20220601.20 gets
released, for now we can replace the shark release link to this on setup_venv.sh to work.
2022-06-01 11:33:53 -07:00
Maksim Levental
5530b56921
Shark Eager Mode jupyter notebook ( #76 )
2022-06-01 09:21:32 -07:00
Ean Garvey
87098e315f
Pass --iree-hal-cuda-llvm-target-arch for GPU execution automatically. ( #66 )
...
* Pass --iree-hal-cuda-llvm-target-arch for GPU execution automatically.
Add IREE CUDA compute capability flag only if sm_70 or later.
* Add Validate Models step to nightly workflow.
2022-06-01 08:38:25 -07:00
Maksim Levental
f57730d2db
Fix type ( #75 )
2022-06-01 08:30:12 -07:00
Vivek Khandelwal
d98d6a065d
Update README.md ( #74 )
2022-06-01 06:53:05 -07:00
Vivek Khandelwal
6081689c9f
Add test for Resnet101 and remove Vgg11 test ( #73 )
2022-06-01 00:49:07 -07:00
Prashant Kumar
04d23e504b
Modify vgg16 to vgg11 to ignore memory limit error.
2022-05-27 21:57:40 +05:30
Prashant Kumar
04291fdfcb
Add vgg and alexnet models to passing tests.
2022-05-27 21:35:02 +05:30
Prashant Kumar
cee02f6a61
Add frontend error checks.
2022-05-27 15:45:45 +05:30
Prashant Kumar
c69baa3b1e
Rename and refactoring.
2022-05-27 15:17:08 +05:30
Prashant Kumar
8294dc3f20
Bug fix related to torch-shark trainer.
2022-05-27 14:50:28 +05:30
Prashant Kumar
e5517f63f5
Add the refactored training module.
2022-05-27 14:21:34 +05:30
powderluv
96acb32fc1
Update test-models.yml
2022-05-26 21:06:20 -07:00
powderluv
a72f727501
Update test-models.yml
2022-05-26 21:03:35 -07:00
Stanley Winata
7b4c7f9bde
Merge pull request #62 from nod-ai/benchmark
...
Add Shark Benchmark
2022-05-26 17:18:55 -07:00
stanley
91867e1fc2
Add Shark Benchmark
...
-Introduce SharkBenchmark that bench models on regular torch, shark-py, and shark-c.
-Integrate iree-benchmark-module into Shark.
2022-05-27 00:07:31 +00:00
Prashant Kumar
18a4423026
Clearing the shark_trainer API for future rework.
2022-05-26 20:15:18 +05:30
Prashant Kumar
15c99adab8
Refactor the whole SharkInference API.
...
1. SharkInference API is refactored to target any frontends or files,
i.e. pytorch, tensorflow, mhlo, linalg, tosa.
2. Refactor all torch APIs.
2022-05-26 18:55:47 +05:30
Eliasj42
ad16e54d4e
updated README ( #61 )
2022-05-25 21:51:02 -07:00
Maksim Levental
ef6f3a7b74
Eager mode with IREE ( #25 )
...
Eager mode with IREE
reenable iree integration
2022-05-25 21:49:19 -07:00
Ean Garvey
772f60c313
Add support for TensorFlow modules + TF miniLM example ( #51 )
2022-05-25 18:50:43 -07:00
Prashant Kumar
737be5be09
Remove AOTModule and update vulkan iree args.
2022-05-25 21:17:17 +05:30
Stanley Winata
c8fcfd6077
Set parallel work as manually configured option ( #58 )
2022-05-24 15:26:28 -07:00
Stanley Winata
5ece8f6f5d
Fix Test Issues on macos ( #57 )
...
-Added a separate pytest config for macos
-Adjusted shark parser to ignore unknown args
2022-05-24 14:40:35 -07:00
Prashant Kumar
6a358cb90a
Update the examples removing functorch dependency.
2022-05-24 19:10:01 +05:30
Prashant Kumar
96577000a3
Remove functorch dependency.
2022-05-24 18:42:35 +05:30
Prashant Kumar
126771fa55
Add gpu tested models.
2022-05-24 11:27:34 +05:30
Prashant Kumar
4b63e0e04a
Add run_on_refbackend and gpu configs. ( #52 )
...
`run_on_refbackend` is added to run linalg_on_tensors_backend compiled
code on torch-mlir's refbackend. Also, added gpu configs and flags.
2022-05-23 14:18:11 -07:00
powderluv
2df9128749
Update README.md
2022-05-23 14:12:55 -07:00
powderluv
c854bfc313
Update nightly.yml
...
remove snapshot name
2022-05-17 12:15:01 -07:00
powderluv
d18adad3e7
Rename python-package.yml to nightly.yml
2022-05-17 08:36:56 -07:00
Prashant Kumar
96c28685ce
Added device map and runs test according to the driver.
...
Automatically runs test according to the device driver present.
2022-05-17 19:33:54 +05:30
