Draft: [onert] block quantization #13693
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
hseok-oh
changed the title
hseok-oh
changed the title
Blockwise quantization: uint4 / int8 with 32 block size, fp16 delta. ONE-DCO-1.0-Signed-off-by: Hyeongseok Oh <[email protected]>
hseok-oh
force-pushed
the
draft/block_quant
branch
from
d602282 to
f4ce5ba
Compare
glistening
reviewed
Aug 27, 2024
nnpackage/schema/circle_schema.fbs
Outdated
| // Represents a specific quantization technique's parameters. | ||
| union QuantizationDetails { | ||
| CustomQuantization, | ||
| CircleBlockQuantization |
There was a problem hiding this comment.
Is the prefix Circle necessary to avoid name conflict from flatbuffers generated files? I guess GGMLBlockQuantization may be better as @jinevening suggested offline. It makes it clear what CircleBlockQuantization means.
hseok-oh
changed the title
hseok-oh
force-pushed
the
draft/block_quant
branch
from
8634ae4 to
d0d592c
Compare
This was referenced Aug 29, 2024
|
All merged |
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Outdated suggestions cannot be applied.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.
Support runtime block quantization: uint4 / int8 with 32 chunk size, fp16 delta.
ONE-DCO-1.0-Signed-off-by: Hyeongseok Oh [email protected]