Efficient decoder text generation wrapper #273
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
|
The documentation is not available anymore as the PR was closed or merged. |
…ent dynamic slice implementation
…able in pipelines
…ause of other complications caused by this.
…he default ipu_config for text-gen pipelines.
jimypbr
changed the title
ncouro-gc
pushed a commit
to graphcore/optimum-graphcore-fork
that referenced
this pull request
Mar 17, 2023
* Set the default matmul_proportion in IPUConfig to 0.2 so default config will work with decoder wrapper
ncouro-gc
pushed a commit
to graphcore/optimum-graphcore-fork
that referenced
this pull request
Mar 17, 2023
* Set the default matmul_proportion in IPUConfig to 0.2 so default config will work with decoder wrapper
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Outdated suggestions cannot be applied.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.
What does this PR do?
Current text generation returns all the logits back from IPU to host. However we only need the logits from the token to be generated. This wraps the model to return only what is necessary to improve the IO performance of the text generation.
Fixes # (issue)
Before submitting