Update QAT READMEs using new APIs#1541
Merged
Merged
Conversation
Summary: #1415 added a quantize_ QAT API for the prepare path. This commit adds the remaining convert path for users to actually perform end-to-end QAT using the quantize_ API. The new flow will look like: ``` from torchao.quantization import ( quantize_, int8_dynamic_activation_int4_weight, ) from torchao.quantization.qat import ( FakeQuantizeConfig, from_intx_quantization_aware_training, intx_quantization_aware_training, ) activation_config = FakeQuantizeConfig(torch.int8, "per_token", is_symmetric=False) weight_config = FakeQuantizeConfig(torch.int4, group_size=32) quantize_( my_model, intx_quantization_aware_training(activation_config, weight_config), ) quantize_(my_model, from_intx_quantization_aware_training()) quantize_(my_model, int8_dynamic_activation_int4_weight(group_size=32)) ``` Test Plan: python test/quantization/test_qat.py -k test_quantize_api_convert_path [ghstack-poisoned]
Add references to new QAT APIs including `quantize_`, `FakeQuantizedX`, and the new embedding Quantizers and ComposableQATQuantizer. Also link to new QAT + LoRA recipe in torchtune. [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1541
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 3dce6a3 with merge base b5b739b ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Add references to new QAT APIs including `quantize_`, `FakeQuantizedX`, and the new embedding Quantizers and ComposableQATQuantizer. Also link to new QAT + LoRA recipe in torchtune. [ghstack-poisoned]
Add references to new QAT APIs including `quantize_`, `FakeQuantizedX`, and the new embedding Quantizers and ComposableQATQuantizer. Also link to new QAT + LoRA recipe in torchtune. [ghstack-poisoned]
Add references to new QAT APIs including `quantize_`, `FakeQuantizedX`, and the new embedding Quantizers and ComposableQATQuantizer. Also link to new QAT + LoRA recipe in torchtune. [ghstack-poisoned]
Add references to new QAT APIs including `quantize_`, `FakeQuantizedX`, and the new embedding Quantizers and ComposableQATQuantizer. Also link to new QAT + LoRA recipe in torchtune. [ghstack-poisoned]
Add references to new QAT APIs including `quantize_`, `FakeQuantizedX`, and the new embedding Quantizers and ComposableQATQuantizer. Also link to new QAT + LoRA recipe in torchtune. [ghstack-poisoned]
Add references to new QAT APIs including `quantize_`, `FakeQuantizedX`, and the new embedding Quantizers and ComposableQATQuantizer. Also link to new QAT + LoRA recipe in torchtune. [ghstack-poisoned]
Add references to new QAT APIs including `quantize_`, `FakeQuantizedX`, and the new embedding Quantizers and ComposableQATQuantizer. Also link to new QAT + LoRA recipe in torchtune. [ghstack-poisoned]
Add references to new QAT APIs including `quantize_`, `FakeQuantizedX`, and the new embedding Quantizers and ComposableQATQuantizer. Also link to new QAT + LoRA recipe in torchtune. [ghstack-poisoned]
Add references to new QAT APIs including `quantize_`, `FakeQuantizedX`, and the new embedding Quantizers and ComposableQATQuantizer. Also link to new QAT + LoRA recipe in torchtune. [ghstack-poisoned]
Add references to new QAT APIs including `quantize_`, `FakeQuantizedX`, and the new embedding Quantizers and ComposableQATQuantizer. Also link to new QAT + LoRA recipe in torchtune. [ghstack-poisoned]
jerryzh168
reviewed
Jan 10, 2025
| ``` | ||
|
|
||
|
|
||
| ### Quantizer API (legacy) |
Contributor
There was a problem hiding this comment.
is there a deprecation plan for this API?
Contributor
Author
There was a problem hiding this comment.
Not yet, but will come up with one
jerryzh168
approved these changes
Jan 10, 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
3 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.
Stack from ghstack (oldest at bottom):
Add references to new QAT APIs including
quantize_,FakeQuantizedX, and the new embedding Quantizers andComposableQATQuantizer. Also link to new QAT + LoRA recipe
in torchtune.
To review on github: Files changed -> README.md -> View file