Add a quantize_symmetric operation and the corresponding CPU kernel #83
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
For now only per-tensor quantization is supported.
dacorvo
force-pushed
the
quantize_kernel
branch
from
557251b
to
d612b6b
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Outdated suggestions cannot be applied.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.
This is mainly to test the library design with a different operation.
The
quantize_symmetricoperation simply rescales and maps the source tensor to eitherint8offloat8.The pull-request also includes a minimal C++ kernel for CPU devices, that only supports per-tensor
int8quantization for now.On a Macbook air, the optimized kernel is only 10 % faster than the default implementation using python torch operators.