Support for on-loading quantization #8
Merged
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
This can be used to pre-configure how we would like the model to be loaded. Right now it supports a configuration for quantization. A design principle of GGMLModelConfig is that it can be used also when the config is NULL - this is why the config_get functions return a gboolean indicating whether there is any change from the default in that part of the configuration and also handle the case where the config object is NULL
…e ModelDescNode We do this after loading the hyperparameters and starting to set up the ModelDesc. The ModelDesc contains all the information about the types of the tensors and since we can convert them now on the fly during loading, this is the perfect place to edit once we know the desired quantization configuration.
smspillaz
force-pushed
the
quantization-conversion-support
branch
from
6659075
to
bba8014
Compare
Its better supported on older platforms
Quantization is imprecise, so we could get slightly different answers depending on the architecture.
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Outdated suggestions cannot be applied.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.
No description provided.