-
Notifications
You must be signed in to change notification settings - Fork 66
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
Composability with sparse and quantization compressors #948
base: main
Are you sure you want to change the base?
Conversation
👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review. |
@@ -37,7 +36,8 @@ def infer_quantization_format( | |||
if save_compressed: | |||
weight_args, input_args = _get_unique_quant_args(model) | |||
is_24_structure = ( | |||
sparsity_config and sparsity_config.sparsity_structure == "2:4" | |||
SparsityStructure(sparsity_structure).value | |||
== SparsityStructure.TWO_FOUR.value |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It seems like we've only enabled this to save using the marlin-24 compressor if the model follows 2:4 sparsity?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: can we not compare the enums directly without .value
?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@kylesayrs accepted
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@dsikka let's sync offline
6b47ecd
to
ea8b8b5
Compare
Increase Sparsity Threshold Signed-off-by: Rahul Tuli <[email protected]>
Signed-off-by: Rahul Tuli <[email protected]>
Signed-off-by: Rahul Tuli <[email protected]>
9249158
to
afc0b5f
Compare
verified decompression works for sparse and quantized model |
This PR enables accomplishes the following: