Add general fake_quantize_affine op #492
Merged
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/492
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ✅ No FailuresAs of commit 9c60424 with merge base 12ac498 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jerryzh168
reviewed
Jul 9, 2024
| @@ -335,6 +378,62 @@ def _dequantize_affine( | |||
|
|
|||
| return dequant.view(original_shape).to(output_dtype) | |||
|
|
|||
|
|
|||
| def _fake_quantize_affine( | |||
There was a problem hiding this comment.
this can be a top level quant primitive I think
jerryzh168
approved these changes
Jul 9, 2024
Summary: Add a general `fake_quantize_affine` op that simulates `quantize_affine` + `dequantize_affine` but without casting the intermediate quantized values to lower bit-widths, intended for quantization-aware training (QAT). Test Plan: python test/quantization/test_quant_primitives.py -k test_fake_quantize_affine
andrewor14
force-pushed
the
fake_quantize_affine
branch
from
3ae3a6a to
9c60424
Compare
dbyoung18
pushed a commit
to dbyoung18/ao
that referenced
this pull request
Jul 31, 2024
Summary: Add a general `fake_quantize_affine` op that simulates `quantize_affine` + `dequantize_affine` but without casting the intermediate quantized values to lower bit-widths, intended for quantization-aware training (QAT). Test Plan: python test/quantization/test_quant_primitives.py -k test_fake_quantize_affine
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
Fixes FP16 + BF16 issue in aoti runner. ``` torchchat % ./cmake-out/aoti_run ./model_bf16.so -z ./.model-artifacts/meta-llama/Llama-2-7b-chat-hf/tokenizer.bin -t 0 -i "Once upon a time" Failed to load ./.model-artifacts/meta-llama/Llama-2-7b-chat-hf/tokenizer.bin into a Tiktoken tokenizer. Trying sentencepiece tokenizer.. Once upon a time, there was a little girl named Lily. She loved to play outside in the sunshine. One day, she saw a big, red ball in the sky. It was the sun! She thought it was so pretty. Lily wanted to play with the ball, but it was too high up in the sky. She tried to jump and reach it, but she couldn't. Then, she had an idea. She would use a stick to get the ball down. Lily found a long stick and tried to reach the ball. She poked and poked, but the ball didn't come down. She was sad. But then, she saw a bird flying by. The bird had a big, red ball in its beak! Lily was so happy! She thanked the bird and played with her new ball all day long. achieved tok/s: 65.842124 ```
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: Add a general
fake_quantize_affineop that simulatesquantize_affine+dequantize_affinebut without casting the intermediate quantized values to lower bit-widths, intended for quantization-aware training (QAT).Test Plan:
python test/quantization/test_quant_primitives.py -k test_fake_quantize_affine