Autoquant #82
Merged
Autoquant #82
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
Summary: Adding autoquantization functionality, using hte do_quant api we can test kernel speeds and pick the best quantization type (or no quantization) for each layer. Test Plan: python test/test.py -k "autoquant" also tested on SAM and SDXL pytorch-labs/segment-anything-fast#114 HDCharles/sdxl-fast@8d9942a Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
facebook-github-bot
added
the
CLA Signed
Merged
cpuhrsch
added a commit
that referenced
this pull request
Mar 26, 2024
cpuhrsch
reviewed
Mar 26, 2024
| from . import dtypes | ||
| from .quantization.quant_api import apply_dynamic_quant | ||
| from .quantization.quant_api import apply_weight_only_int8_quant | ||
|
|
||
| __all__ = [ |
There was a problem hiding this comment.
I don't think we should make all of these public right away. Like apply_dynamic_quant is a bit of a duplicate of change_linear_weights_to_int8_dqtensors and swap_conv2d_1x1_to_linear might be something we just want to do automatically instead of making it a toplevel API.
Also dtypes is twice.
Is it possible to only add autoquant for now?
cpuhrsch
reviewed
Mar 26, 2024
| @@ -136,10 +143,14 @@ def apply_dynamic_quant(model, filter_fn=None): | |||
|
|
|||
|
|
|||
| def _get_subclass_inserter(cls, **kwargs): | |||
|
|
|||
| # pyre-fixme[53]: Captured variable `cls` is not annotated. | |||
There was a problem hiding this comment.
You don't need the pyre-fixmes anymore
cpuhrsch
pushed a commit
that referenced
this pull request
Apr 1, 2024
Summary: Adding autoquantization functionality, using hte do_quant api we can test kernel speeds and pick the best quantization type (or no quantization) for each layer. Test Plan: python test/test.py -k "autoquant" also tested on SAM and SDXL pytorch-labs/segment-anything-fast#114 HDCharles/sdxl-fast@8d9942a Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
cpuhrsch
added a commit
that referenced
this pull request
Apr 5, 2024
dbyoung18
pushed a commit
to dbyoung18/ao
that referenced
this pull request
Jul 31, 2024
Summary: Adding autoquantization functionality, using hte do_quant api we can test kernel speeds and pick the best quantization type (or no quantization) for each layer. Test Plan: python test/test.py -k "autoquant" also tested on SAM and SDXL pytorch-labs/segment-anything-fast#114 HDCharles/sdxl-fast@8d9942a Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
dbyoung18
pushed a commit
to dbyoung18/ao
that referenced
this pull request
Jul 31, 2024
This reverts commit 8119319.
dbyoung18
pushed a commit
to dbyoung18/ao
that referenced
this pull request
Jul 31, 2024
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.
Summary: Adding autoquantization functionality, using hte do_quant api we can test kernel speeds and pick the best quantization type (or no quantization) for each layer.
Test Plan: python test/test.py -k "autoquant"
also tested on SAM and SDXL
pytorch-labs/segment-anything-fast#114 HDCharles/sdxl-fast@8d9942a
Reviewers:
Subscribers:
Tasks:
Tags:
[ghstack-poisoned]