github/AMD-SHARK-Studio
1
1
Fork 0
mirror of https://github.com/nod-ai/AMD-SHARK-Studio.git synced 2026-02-19 11:56:43 -05:00
Code Issues Packages Projects Releases Wiki Activity
379 Commits 66 Branches 705 Tags
IntelGPU
Commit Graph

52 Commits

Author SHA1 Message Date
Stanley Winata
c47218c972 WIP: Intel-GPU integration 2022-08-10 11:24:00 -07:00
Prashant Kumar
4e5c592094 Enable --devices to pass through CLI. 2022-07-27 22:13:52 +05:30
Prashant Kumar
39c5f940c9 Add v_diffusion model into shark examples. (#195) 2022-07-19 09:51:10 -07:00
Prashant Kumar
54a642e76a Update the resnet50 example to use the shark_downloader. 
The resnet50 example is updated to use the shark_downloader instead
of shark_importer and inference.
 2022-07-18 13:41:38 +05:30
Prashant Kumar
1191f53c9d Add the shark_downloader for the torch_models. (#184) 2022-07-14 13:41:43 -07:00
Prashant Kumar
0dcf387089 Add shark_importer for torch_models. (#183) 
All the torch_models are imported to gs::shark_tank.
Scripts have been updated.
 2022-07-12 20:38:19 -07:00
Prashant Kumar
2e5cb4ba76 Add resnest model to the shark_inference examples list. 2022-07-07 19:51:53 +05:30
Anush Elangovan
a7435973d9 Fix black formatting 2022-06-30 20:42:02 +00:00
Prashant Kumar
83855e7b08 Capture input information from mlir_graph and generate random inputs. 2022-06-29 22:51:53 +05:30
Prashant Kumar
b07377cbfd Refactor the shark_runner shark_inference to only support mlir_modules. 
1. The shark_inference is divided into shark_importer and
   shark_inference.
2. All the tank/pytorch tests have been updated.
 2022-06-28 18:46:18 +05:30
Prashant Kumar
e8aa105b2a Divide iree_utils and do module imports on function calls. 2022-06-22 14:17:33 +05:30
Prashant Kumar
334d129443 Changes to minilm to make it one on one with tensorflow. 2022-06-21 22:08:59 +05:30
Prashant Kumar
4d3acff484 Add tf masked lm models (17 models - 12 pass, 5 fail). (#135) 2022-06-16 07:28:00 -07:00
Prashant Kumar
bf02c8d0db Add t5(https://huggingface.co/docs/transformers/model_doc/t5) model. 2022-06-08 16:25:23 +00:00
Prashant Kumar
1394255fc9 Add gpt2 model(https://huggingface.co/distilgpt2) via tensorflow 
frontend.
 2022-06-08 18:06:35 +05:30
Prashant Kumar
d86ca8e174 Add inference of https://huggingface.co/openai/clip-vit-base-patch32 
via tensorflow pipeline.
 2022-06-08 18:03:36 +05:30
Stanley Winata
c70ab55717 Add saving and loading of mlir to run. (#89) 2022-06-05 08:42:40 -07:00
Stanley Winata
276dcf1441 Add benchmark for TF (#87) 
-Refactor SharkBenchmarker to run TF
-Add example and test to benchmark TF
 2022-06-03 22:10:27 -07:00
yzhang93
16c50cac15 Add the option to use tuned model in shark_runner (#79) 2022-06-02 18:25:33 -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
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
Prashant Kumar
c69baa3b1e Rename and refactoring. 2022-05-27 15:17:08 +05:30
Prashant Kumar
e5517f63f5 Add the refactored training module. 2022-05-27 14:21:34 +05:30
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
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
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
6a358cb90a Update the examples removing functorch dependency. 2022-05-24 19:10:01 +05:30
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
Prashant Kumar
0bd5f22f63 Remove redundant examples. 2022-05-17 17:50:16 +05:30
Prashant Kumar
63f9b206ac Modify pytest to run a certain test. 2022-05-17 16:58:08 +05:30
Prashant Kumar
dcc1bbac14 Add pytests-parametrize with device and dynamic option. 
Added pytests-parametrize with device and dynamic options, also
added worker flag in pytest to run tests concurrently.
 2022-05-17 11:07:56 +05:30
Vivek Khandelwal
5dfe5ba5fc Add Squeezenet Vision model test in test_cpu.py 2022-05-13 13:25:22 +05:30
Vivek Khandelwal
4e7b3f66f6 Add function for models benchmarking 2022-05-10 22:37:42 +05:30
Prashant Kumar
bd6409f34c Add fullyconnected training example. 2022-05-10 21:28:02 +05:30
Prashant Kumar
dd4bfc9c99 Update the shark-trainer API. 
Shark-trainer API now has num_iters parameter for training.
 2022-05-10 21:25:09 +05:30
Prashant Kumar
f590bd56c3 Add bert_training example. 2022-05-06 21:57:46 +05:30
Prashant Kumar
b4114c0938 Make backward API workable. 2022-05-06 14:51:44 +05:30
Prashant Kumar
08df345fbc Add make_fx whole graph extract. 2022-05-04 20:58:59 +05:30
Vivek Khandelwal
7f6159462d Add num_iterations and num_warmup_iterations args. 2022-05-04 20:38:19 +05:30
Prashant Kumar
db5be15310 Centralize the parser location. Also add the --device flag. 
Centralized the shark_args parser. Also added the --device flag that
specifies the device on which the inference or training is to be done.
 2022-05-02 15:35:22 +05:30
Prashant Kumar
bd212634c1 Add CI for testing of various models. (#28) 
Added pytest CI for testing for Pytorch Inference and vision models.
 2022-04-27 06:52:49 -07:00
Prashant Kumar
3ed5a9c84e Change the python import of shark. 2022-04-26 20:55:33 +05:30
Prashant Kumar
37468f7bb8 Enable Shark Trainer APIs 2022-04-21 20:31:30 +05:30