[Relay][Quantization] Speed-aware quantization scheme improvement #2723
Conversation
This file contains hidden or 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
vinx13
force-pushed
the
feature/quanti_improve
branch
from
865b37c to
4996286
Compare
ZihengJiang
reviewed
Mar 5, 2019
tqchen
previously requested changes
Mar 5, 2019
|
for the comment, I mean to explain the code like here |
ZihengJiang
approved these changes
Mar 8, 2019
|
please fixed the CI @vinx13 |
vinx13
force-pushed
the
feature/quanti_improve
branch
from
807b5cd to
59474d2
Compare
ZihengJiang
approved these changes
Mar 9, 2019
|
Merged, thanks! @vinx13 |
wweic
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Mar 9, 2019
…ache#2723) * [Relay][Quantization] Speed-aware quantization scheme improvement * Add comment * Add use_stop_fusion to qconfig * Update comment
wweic
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Mar 12, 2019
…ache#2723) * [Relay][Quantization] Speed-aware quantization scheme improvement * Add comment * Add use_stop_fusion to qconfig * Update comment
wweic
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Mar 12, 2019
…ache#2723) * [Relay][Quantization] Speed-aware quantization scheme improvement * Add comment * Add use_stop_fusion to qconfig * Update comment
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Writing int32 result to global memory can be much slower than int8. This PR does the following change:
add_rewrite, quantize rhs to int8 so that read/write of rhs can be performed in int8.UnifyDtypeScale, if the input is simulated_quantize(QInput), cast the input to int8 before casting to int32.@ZihengJiang