Conversation
Contributor
Author
|
Stack from ghstack (oldest at bottom): |
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3491
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 1 PendingAs of commit 00a23fa with merge base ff6d9e2 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
vkuzo
added a commit
that referenced
this pull request
Dec 15, 2025
Summary: Moves the following workflows to prototype: * Int8DynamicActivationInt4WeightConfig * Int4DynamicActivationInt4WeightConfig * GemliteUIntXWeightOnlyConfig * Float8StaticActivationFloat8WeightConfig * UIntXWeightOnlyConfig * FPXWeightOnlyConfig Specifically: 1. move the deprecated workflows to `torchao/prototype/quantization/quant_api.py` 2. move utils to `torchao/quantization/utils.py` as needed 3. make some imports happen at runtime to avoid circular imports 4. change the warnings in the six workflows to reflect their new state For now, keep BC by importing them from the old location. So, we get the benefits of the simpler `quant_api.py` file with this PR, and we will defer breaking BC until a future time to amortize the eng cost. Test Plan: CI Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 6e22be1 ghstack-comment-id: 3657392357 Pull-Request: #3491
17 tasks
vkuzo
added a commit
that referenced
this pull request
Dec 15, 2025
Summary: Moves the following workflows to prototype: * Int8DynamicActivationInt4WeightConfig * Int4DynamicActivationInt4WeightConfig * GemliteUIntXWeightOnlyConfig * Float8StaticActivationFloat8WeightConfig * UIntXWeightOnlyConfig * FPXWeightOnlyConfig Specifically: 1. move the deprecated workflows to `torchao/prototype/quantization/quant_api.py` 2. move utils to `torchao/quantization/utils.py` as needed 3. make some imports happen at runtime to avoid circular imports 4. change the warnings in the six workflows to reflect their new state For now, keep BC by importing them from the old location. So, we get the benefits of the simpler `quant_api.py` file with this PR, and we will defer breaking BC until a future time to amortize the eng cost. Test Plan: CI Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: e06f561 ghstack-comment-id: 3657392357 Pull-Request: #3491
vkuzo
commented
Dec 15, 2025
|
|
||
| Our framework makes it straightforward to add tensor parallel support to your custom quantized tensor subclass. Check out our [tensor parallel tutorial](tutorials/developer_api_guide/tensor_parallel.py) to see how a quantized tensor subclass can be extended to support column and row-wise tensor sharding while maintaining compatibility with `torch.compile`. | ||
|
|
||
| ### Custom Kernels |
Contributor
Author
There was a problem hiding this comment.
this is no longer relevant
vkuzo
added a commit
that referenced
this pull request
Dec 15, 2025
Summary: Moves the following workflows to prototype: * Int8DynamicActivationInt4WeightConfig * Int4DynamicActivationInt4WeightConfig * GemliteUIntXWeightOnlyConfig * Float8StaticActivationFloat8WeightConfig * UIntXWeightOnlyConfig * FPXWeightOnlyConfig Specifically: 1. move the deprecated workflows to `torchao/prototype/quantization/quant_api.py` 2. move utils to `torchao/quantization/utils.py` as needed 3. make some imports happen at runtime to avoid circular imports 4. change the warnings in the six workflows to reflect their new state For now, keep BC by importing them from the old location. So, we get the benefits of the simpler `quant_api.py` file with this PR, and we will defer breaking BC until a future time to amortize the eng cost. Test Plan: CI Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: c43b02e ghstack-comment-id: 3657392357 Pull-Request: #3491
vkuzo
added a commit
that referenced
this pull request
Dec 16, 2025
Summary: Moves the following workflows to prototype: * Int8DynamicActivationInt4WeightConfig * Int4DynamicActivationInt4WeightConfig * GemliteUIntXWeightOnlyConfig * Float8StaticActivationFloat8WeightConfig * UIntXWeightOnlyConfig * FPXWeightOnlyConfig Specifically: 1. move the deprecated workflows to `torchao/prototype/quantization/quant_api.py` 2. move utils to `torchao/quantization/utils.py` as needed 3. make some imports happen at runtime to avoid circular imports 4. change the warnings in the six workflows to reflect their new state For now, keep BC by importing them from the old location. So, we get the benefits of the simpler `quant_api.py` file with this PR, and we will defer breaking BC until a future time to amortize the eng cost. Test Plan: CI Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 30d8a0d ghstack-comment-id: 3657392357 Pull-Request: #3491
vkuzo
added a commit
that referenced
this pull request
Dec 16, 2025
Summary: Moves the following workflows to prototype: * Int8DynamicActivationInt4WeightConfig * Int4DynamicActivationInt4WeightConfig * GemliteUIntXWeightOnlyConfig * Float8StaticActivationFloat8WeightConfig * UIntXWeightOnlyConfig * FPXWeightOnlyConfig Specifically: 1. move the deprecated workflows to `torchao/prototype/quantization/quant_api.py` 2. move utils to `torchao/quantization/utils.py` as needed 3. make some imports happen at runtime to avoid circular imports 4. change the warnings in the six workflows to reflect their new state For now, keep BC by importing them from the old location. So, we get the benefits of the simpler `quant_api.py` file with this PR, and we will defer breaking BC until a future time to amortize the eng cost. Test Plan: CI Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 2ecf4d8 ghstack-comment-id: 3657392357 Pull-Request: #3491
vkuzo
added a commit
that referenced
this pull request
Dec 16, 2025
Summary: Moves the following workflows to prototype: * Int8DynamicActivationInt4WeightConfig * Int4DynamicActivationInt4WeightConfig * GemliteUIntXWeightOnlyConfig * Float8StaticActivationFloat8WeightConfig * UIntXWeightOnlyConfig * FPXWeightOnlyConfig Specifically: 1. move the deprecated workflows to `torchao/prototype/quantization/quant_api.py` 2. move utils to `torchao/quantization/utils.py` as needed 3. make some imports happen at runtime to avoid circular imports 4. change the warnings in the six workflows to reflect their new state For now, keep BC by importing them from the old location. So, we get the benefits of the simpler `quant_api.py` file with this PR, and we will defer breaking BC until a future time to amortize the eng cost. Test Plan: CI Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 4b7b474 ghstack-comment-id: 3657392357 Pull-Request: #3491
vkuzo
added a commit
that referenced
this pull request
Dec 16, 2025
Summary: Moves the following workflows to prototype: * Int8DynamicActivationInt4WeightConfig * Int4DynamicActivationInt4WeightConfig * GemliteUIntXWeightOnlyConfig * Float8StaticActivationFloat8WeightConfig * UIntXWeightOnlyConfig * FPXWeightOnlyConfig Specifically: 1. move the deprecated workflows to `torchao/prototype/quantization/quant_api.py` 2. move utils to `torchao/quantization/utils.py` as needed 3. make some imports happen at runtime to avoid circular imports 4. change the warnings in the six workflows to reflect their new state For now, keep BC by importing them from the old location. So, we get the benefits of the simpler `quant_api.py` file with this PR, and we will defer breaking BC until a future time to amortize the eng cost. Test Plan: CI Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 454af42 ghstack-comment-id: 3657392357 Pull-Request: #3491
jerryzh168
approved these changes
Dec 17, 2025
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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:
Moves the following workflows to prototype:
Specifically:
torchao/prototype/quantization/quant_api.pytorchao/quantization/utils.pyas neededFor now, keep BC by importing them from the old location. So, we get the
benefits of the simpler
quant_api.pyfile with this PR, and we will defer breakingBC until a future time to amortize the eng cost.
Test Plan:
CI
Reviewers:
Subscribers:
Tasks:
Tags: