[Text Generation] Detect dtype of kv cache (float32/uint8) for text generation models #1123
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
bfineran
approved these changes
Jul 17, 2023
|
let's add test plan to the description |
|
@bfineran but the appropriate tests are laid out in detail in the sparseml counterpart. |
Satrat
reviewed
Jul 18, 2023
Satrat
reviewed
Jul 18, 2023
Satrat
approved these changes
Jul 18, 2023
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Outdated suggestions cannot be applied.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.
The
NLDecoderEnginecan now infer the dtype of the kv cache input from the onnx graph. This is necessary in order to enforce the adequate dtype when creating an initial kv cache arrays.The PR is complementary to neuralmagic/sparseml#1648. Refer to that PR for manual tests description.