Stella Laurenzo cec6eda6b4 Optimize device enumeration overhead and log details on long operations. (#1734) ...

* Optimize device enumeration overhead and log details on long operations.

* Various fixes to add `@functools.cache` to what should be one time, expensive, device enumeration and setup activities. Cuts several seconds off of initialization on my machine.
* Add detailed tracing to actual invocations if they exceed a certain timeout or have an exception.
* Add detailed tracing to loading status.
* By default detail logging is only printed if an operation takes an excessive amount of time. All logging/timing can be printed by setting the variable `$env:SHARK_DETAIL_TRACE = "1"`

* Remove cache from unhashable functions

2023-08-07 17:20:53 -07:00

..

dynamo_backend

Make the tensors contiguous.

2023-06-26 17:29:54 +05:30

examples

update upscalar example

2023-07-28 21:06:28 +05:30

iree_utils

Optimize device enumeration overhead and log details on long operations. (#1734)

2023-08-07 17:20:53 -07:00

shark_eager

Add shark_eager mode.

2023-06-22 22:59:14 +05:30

tests

Add stress test

2022-12-13 13:21:51 -08:00

__init__.py

Add the shark compile downstream due to https://github.com/pytorch/pytorch/pull/104185#issuecomment-1615110613 (#1615)

2023-07-01 08:30:58 -07:00

backward_makefx.py

Minor fixes for MiniLM Training

2023-07-18 17:16:44 +05:30

iree_eager_backend.py

[SharkInference] Make SharkInference compile the entire module (#708)

2023-01-03 23:25:23 +05:30

model_annotation.py

Modify the lowering config format for SPIRVMatmulPromoteVectorize pipeline (#1471)

2023-05-29 21:53:48 -07:00

parser.py

Move vulkan runtime flags to shark_args

2023-07-28 21:06:28 +05:30

shark_benchmark_runner.py

Separate pytest benchmark modes and fix model updates for SHARK downloader / pytest. (#1264)

2023-04-03 08:24:21 -07:00

shark_compile.py

[MiniGPT4] Add MiniGPT4 to SHARK (#1554)

2023-07-25 09:42:27 -07:00

shark_downloader.py

fix name check for file existence

2023-08-05 21:33:53 +05:30

shark_generate_model_config.py

Add GPU ID's in model_confg.json by default for manual annotation (#1718)

2023-08-04 12:46:27 -05:00

shark_importer.py

Fix vicuna script (#1697)

2023-07-27 17:24:26 -05:00

shark_inference.py

[SharkInference-SharkRuntime] Adds capability to mmap vmfbs

2023-06-22 20:43:40 +05:30

shark_runner.py

[SharkInference-SharkRuntime] Adds capability to mmap vmfbs

2023-06-22 20:43:40 +05:30

shark_trainer.py

Change instances of input_type='mhlo' to 'auto' (#1482)

2023-06-02 16:43:47 -05:00

stress_test.py

Fix concurrency issue in stress_test for CUDA devices

2022-12-22 08:54:19 -08:00

tflite_utils.py

Remove tf package dep for SharkDownloader tflite tests (#212)

2022-07-26 12:41:12 -07:00

torch_mlir_lockstep_tensor.py

[Lockstep] Hack to avoid aten._reshape_alias (#332)

2022-09-22 18:02:09 -04:00

torch_mlir_utils.py

Add mlir_type for torch_model_list.csv (#1428)

2023-05-15 10:23:54 -07:00