fix: full gpu hybrid model #963
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
andrei-stoian-zama
force-pushed
the
chore/optimize_mem_and_runtime_fhe_disable
branch
from
43601e1 to
2a326f3
Compare
|
Coverage passed ✅Coverage details
|
kcelia
reviewed
Jan 6, 2025
| @@ -730,14 +730,18 @@ def _quantize_layers(self, *input_calibration_data: numpy.ndarray): | |||
| node_results[output_name] = node_output[0] | |||
| constants.add(output_name) | |||
|
|
|||
| def quantize_module(self, *calibration_data: numpy.ndarray) -> QuantizedModule: | |||
| def quantize_module( | |||
| self, *calibration_data: numpy.ndarray, keep_onnx: Optional[bool] = True | |||
There was a problem hiding this comment.
you mean keep_onnx: Optional[bool] = None ? or keep_onnx: bool = True
kcelia
reviewed
Jan 6, 2025
| @@ -686,6 +691,8 @@ def quant(self, values: numpy.ndarray) -> numpy.ndarray: | |||
| assert self.offset is not None | |||
| assert self.scale is not None | |||
|
|
|||
| assert dtype in (numpy.int64, numpy.int32, numpy.float32, numpy.float64) | |||
There was a problem hiding this comment.
maybe:
valid_dtypes = (numpy.int64, numpy.int32, numpy.float32, numpy.float64)
assert dtype in valid_dtypes, f"Invalid dtype: `{dtype}`. Expected one of {valid_dtypes}."
kcelia
reviewed
Jan 6, 2025
| "\u001b[0;31mNotImplementedError\u001b[0m: GLWE backend deployment is not yet supported" | ||
| ] | ||
| } | ||
| ], |
There was a problem hiding this comment.
~~There are 2 errors in this notebook~
NotImplementedError: GLWE backend deployment is not yet supported
AssertionError: assert self.private_key is not None`
There was a problem hiding this comment.
I fixed and re-ran this notebook in #969
There was a problem hiding this comment.
jfrery
approved these changes
Jan 6, 2025
andrei-stoian-zama
deleted the
chore/optimize_mem_and_runtime_fhe_disable
branch
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.
Closes https://github.com/zama-ai/concrete-ml-internal/issues/4682