This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
INC quantization tutorial #20889
Merged
INC quantization tutorial #20889
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
PawelGlomski-Intel
requested review from
szha and
aaronmarkham
as code owners
|
Hey @PawelGlomski-Intel , Thanks for submitting the PR
CI supported jobs: [unix-gpu, unix-cpu, windows-cpu, sanity, centos-gpu, website, miscellaneous, clang, centos-cpu, edge, windows-gpu] Note: |
mseth10
added
pr-awaiting-testing
bartekkuncer
approved these changes
Feb 11, 2022
docs/python_docs/python/tutorials/performance/backend/mkldnn/mkldnn_quantization.md
Outdated
Show resolved
Hide resolved
| toc = time.time() | ||
| logging.info('Time cost=%.2fs', toc - tic) | ||
|
|
||
| # we choose the best model assuming higher score stands for better model quality |
There was a problem hiding this comment.
Some comments start from capital letter some from a small one in both *.py files.
anko-intel
approved these changes
Feb 11, 2022
…kldnn_quantization.md Co-authored-by: bartekkuncer <bartosz.kuncer@intel.com>
mseth10
added
pr-awaiting-testing
|
@mxnet-bot run ci [unix-cpu, unix-gpu, website] |
|
Jenkins CI successfully triggered : [unix-gpu, website, unix-cpu] |
mseth10
added
pr-awaiting-testing
|
@mxnet-bot run ci [unix-cpu, website] |
|
Jenkins CI successfully triggered : [unix-cpu, website] |
mseth10
added
pr-awaiting-testing
josephevans
pushed a commit
that referenced
this pull request
Mar 9, 2022
* Add inc to quantization documentation * Minor fixes * review fixes * fix * fix2 * Add BERT example with results, review fixes * Add results from aws machine (with VNNI instructions) * Small fix * Fix mxnet installation instruction * Review fixes * Review fixes
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
Description
This change extends MKLDNN quantization tutorial with quantization and auto-tuning using Intel® Neural Compressor.