-
Notifications
You must be signed in to change notification settings - Fork 141
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Draft: Full quantization on runtime (WIP) #12903
Draft
hseok-oh
wants to merge
4
commits into
Samsung:master
Choose a base branch
from
hseok-oh:draft/full_quantize
base: master
Could not load branches
Branch not found: {{ refName }}
Could not load tags
Nothing to show
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
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
63d7cc6
to
fa50dd8
Compare
fccd8c8
to
f2133ea
Compare
781782e
to
7963372
Compare
7963372
to
8611538
Compare
This was referenced May 16, 2024
6d380a3
to
76ce69e
Compare
This was referenced May 27, 2024
Create and register observers on execution, not compilation. It is more flexible and allows for more dynamic observation (ex. profile, dump on demand) ONE-DCO-1.0-Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com> Remove compile option: minmax_filepath, trace_filepath create on compile, check usage on execution move file creation introduce execution config and context Use workspace in compiler option
full quantization - use minmax-embedder Copy embedder into odc directory: HDF5 build issue Revert hdf5 version up and build Use different env variable to get minmax data rename onert_run quantize parameter Remove hdf5 dependency on minmax embedding restruct quantizer restruct test library: random input generation for each run, dump use workspace for quantization configuration API
76ce69e
to
d7d8c5d
Compare
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.
Call full quantization path on on-device quantization (use #11497)