-
Notifications
You must be signed in to change notification settings - Fork 6.8k
Conversation
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: |
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Outdated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.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Some comments start from capital letter some from a small one in both *.py files.
…kldnn_quantization.md Co-authored-by: bartekkuncer <bartosz.kuncer@intel.com>
@mxnet-bot run ci [unix-cpu, unix-gpu, website] |
Jenkins CI successfully triggered : [unix-gpu, website, unix-cpu] |
@mxnet-bot run ci [unix-cpu, website] |
Jenkins CI successfully triggered : [unix-cpu, website] |
* 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
Description
This change extends MKLDNN quantization tutorial with quantization and auto-tuning using Intel® Neural Compressor.