Added flux demo #3418
Open
Added flux demo #3418
Conversation
This file contains 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
github-actions
bot
added
component: conversion
peri044
reviewed
Feb 27, 2025
narendasan
reviewed
Feb 27, 2025
cehongwang
force-pushed
the
flux-demo
branch
from
b2eb297 to
6d36077
Compare
|
Can the app display the inference time, might be nice to have some stats rendered live as you generate |
cehongwang
force-pushed
the
flux-demo
branch
4 times, most recently
from
48a7c94 to
5a528f1
Compare
narendasan
reviewed
Mar 18, 2025
cehongwang
force-pushed
the
flux-demo
branch
6 times, most recently
from
361fb76 to
0aeea36
Compare
cehongwang
force-pushed
the
flux-demo
branch
4 times, most recently
from
9964674 to
cfbc9ea
Compare
narendasan
reviewed
Mar 26, 2025
narendasan
reviewed
Mar 26, 2025
py/torch_tensorrt/dynamo/runtime/_MutableTorchTensorRTModule.py
Outdated
Show resolved
Hide resolved
narendasan
reviewed
Mar 26, 2025
narendasan
reviewed
Mar 26, 2025
narendasan
reviewed
Mar 26, 2025
|
Also rebase |
peri044
reviewed
Mar 26, 2025
Comment on lines
+309
to
+325
| if self.allow_complex_guards_as_runtime_asserts: | ||
| return _export( | ||
| self.original_model, | ||
| self.arg_inputs, | ||
| kwargs=self.kwarg_inputs, | ||
| dynamic_shapes=self._get_total_dynamic_shapes(), | ||
| strict=self.strict, | ||
| allow_complex_guards_as_runtime_asserts=self.allow_complex_guards_as_runtime_asserts, | ||
| ) | ||
| else: | ||
| return torch.export.export( | ||
| self.original_model, | ||
| self.arg_inputs, | ||
| kwargs=self.kwarg_inputs, | ||
| dynamic_shapes=self._get_total_dynamic_shapes(), | ||
| strict=self.strict, | ||
| ) |
There was a problem hiding this comment.
I think let's do a try catch style here where we try torch.export.export first and then _trace.export. I found _export doesn't work with modelopt recently.
There was a problem hiding this comment.
Catch style will make the process slower because it needs to try one and the other, right? My thoughts here is have the user decide whether they have to use allow_complex_guards_as_runtime_asserts, which only _export has. If that is absolute necessary, then we cannot use torch.export.export.
…daGraph and Weight streaming
cehongwang
force-pushed
the
flux-demo
branch
4 times, most recently
from
2ad38e3 to
b254581
Compare
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
Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.
Fixes # (issue)
Type of change
Please delete options that are not relevant and/or add your own.
Checklist: