chore/fix: Restructure Dynamo directory [7 / x] #1981
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
gs-olive
added
component: dynamo
gs-olive
force-pushed
the
dynamo_general_purpose_acceleration
branch
from
a3dd0c8 to
2003b07
Compare
gs-olive
force-pushed
the
dynamo_folder_refactoring
branch
from
5024e4a to
4ed3e3f
Compare
gs-olive
force-pushed
the
dynamo_folder_refactoring
branch
from
4ed3e3f to
d48d5c1
Compare
gs-olive
force-pushed
the
dynamo_folder_refactoring
branch
from
d48d5c1 to
ea64529
Compare
narendasan
reviewed
Jun 7, 2023
| @@ -8,10 +8,10 @@ | |||
| from torch_tensorrt import EngineCapability, Device | |||
| from torch_tensorrt.fx.utils import LowerPrecision | |||
|
|
|||
| from torch_tensorrt.dynamo.backend._settings import CompilationSettings | |||
| from torch_tensorrt.dynamo.common import CompilationSettings | |||
There was a problem hiding this comment.
do you think its worth having dynamo.common.CompilationSettings vs just dynamo.CompilationSettings?
There was a problem hiding this comment.
I think it would be better as dynamo.common.CompilationSettings until both compile and export use them, since dynamo.CompilationSettings might imply it is used across dynamo, whereas common could just be general purpose utilities.
| from torch_tensorrt.dynamo.backend.utils import prepare_inputs, prepare_device | ||
| from torch_tensorrt.dynamo.backend.backends import torch_tensorrt_backend | ||
| from torch_tensorrt.dynamo.backend._defaults import ( | ||
| from torch_tensorrt.dynamo.common._defaults import ( |
There was a problem hiding this comment.
This one, I am more open to moving up a level since the necessary changes have been made to both compile and export. I could add from torch_tensorrt.dynamo.common import _defaults to the torch_tensorrt.dynamo.__init__.py
gs-olive
force-pushed
the
dynamo_general_purpose_acceleration
branch
from
2003b07 to
9e805d1
Compare
gs-olive
force-pushed
the
dynamo_folder_refactoring
branch
from
ea64529 to
ece13a7
Compare
gs-olive
commented
Jun 28, 2023
Comment on lines
143
to
150
| use_experimental_rt=use_experimental_rt, | ||
| max_aux_streams=max_aux_streams, | ||
| version_compatible=version_compatible, | ||
| optimization_level=optimization_level, |
There was a problem hiding this comment.
Similar fixes in #1997 - to rebase after merge.
gs-olive
force-pushed
the
dynamo_folder_refactoring
branch
from
f851dd0 to
c62f30b
Compare
gs-olive
force-pushed
the
dynamo_folder_refactoring
branch
from
c62f30b to
fc85356
Compare
gs-olive
force-pushed
the
dynamo_compile_trt_module_next
branch
from
487ba93 to
49cd3a6
Compare
gs-olive
force-pushed
the
dynamo_folder_refactoring
branch
from
fc85356 to
d2fcab0
Compare
gs-olive
force-pushed
the
dynamo_compile_trt_module_next
branch
from
49cd3a6 to
e2594b6
Compare
gs-olive
force-pushed
the
dynamo_folder_refactoring
branch
from
d2fcab0 to
369f442
Compare
gs-olive
force-pushed
the
dynamo_compile_trt_module_next
branch
3 times, most recently
from
c0f0a22 to
1756b12
Compare
gs-olive
force-pushed
the
dynamo_folder_refactoring
branch
from
369f442 to
43b18c8
Compare
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
There was a problem hiding this comment.
There are some changes that do not conform to Python style guidelines:
--- py/torch_tensorrt/dynamo/fx_ts_compat/lower.py 2023-07-07 22:21:04.022422 +0000
+++ py/torch_tensorrt/dynamo/fx_ts_compat/lower.py 2023-07-07 22:21:19.929000 +0000
@@ -8,11 +8,15 @@
import torch.fx as fx
import torch.nn as nn
import torch_tensorrt.fx.tracer.dispatch_tracer.aten_tracer as aten_tracer
from torch.fx.passes.splitter_base import SplitResult
-from torch_tensorrt.dynamo.common import TRTInterpreter, TRTInterpreterResult, use_python_runtime_parser
+from torch_tensorrt.dynamo.common import (
+ TRTInterpreter,
+ TRTInterpreterResult,
+ use_python_runtime_parser,
+)
from .lower_setting import LowerSetting
from .passes.lower_pass_manager_builder import LowerPassManagerBuilder
from .passes.pass_utils import PassFunc, validate_inference
from torch_tensorrt.fx.tools.timing_cache_utils import TimingCacheManager
from torch_tensorrt.fx.tools.trt_splitter import TRTSplitter, TRTSplitterSetting
- Add `common` directory which stores code common to both the compile and export path, to reduce code duplication and better organize the repository - Update necessary imports, promote the `_defaults` module to `torch_tensorrt.dynamo._defaults`
gs-olive
force-pushed
the
dynamo_folder_refactoring
branch
from
43b18c8 to
db3523a
Compare
|
Closed in favor of unified restructuring PR. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
commondirectory which stores code common to both the compile and export path, to reduce code duplication and better organize the repositoryfx_ts_compatfx_ts_compatto agree with those incompileType of change
Please delete options that are not relevant and/or add your own.
Checklist: