This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
AMP improvements + enable bf16 input for quantize_v2 #20983
Merged
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Outdated suggestions cannot be applied.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.
Changes
asnumpy()
for bfloat16 dtypeLP16_FP32_FUNCS
list, for which order of visited nodes during graph pass could have affected whether an op is converted (to low precision) or not.tests/python/amp/common.py
quantize_v2
ops (removes the need foramp_cast
beforequantize_v2
for quantized models)