Add INT8 support to fbgemm qcomm lib #1337
Closed
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
✅ Deploy Preview for eclectic-stroopwafel-199537 canceled.
|
|
This pull request was exported from Phabricator. Differential Revision: D39473386 |
Summary: Pull Request resolved: pytorch#1337 Add INT8 codec to fbgemm library. Also defined a context class to pass the row_dim and row_dim_quant parameters during coding and encoding. For INT8, the output size is decided by row dim, which is needed by high level collective communication modules. To that purpose, this diff adds a new calc_quantized_size function and implement it based on the INT8 codec logic. Differential Revision: D39473386 fbshipit-source-id: 445060348bbda368c8c5a8df1bd60c60a0be12c3
yusuo
force-pushed
the
export-D39473386
branch
from
6177cdc
to
29a8f95
Compare
|
This pull request was exported from Phabricator. Differential Revision: D39473386 |
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Outdated suggestions cannot be applied.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 INT8 codec to fbgemm library. Also defined a context class to pass the row_dim and row_dim_quant parameters during coding and encoding.
For INT8, the output size is decided by row dim, which is needed by high level collective communication modules. To that purpose, this diff adds a new calc_quantized_size function and implement it based on the INT8 codec logic.
Differential Revision: D39473386