fix dim issue of next_token_logits in sample, or else logits_processo… #301
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
|
@regisss @yao-matrix please have a review. |
|
The documentation is not available anymore as the PR was closed or merged. |
regisss
approved these changes
Jul 19, 2023
|
@sywangyi You should have received an invitation to join the collaborators of this repo. That way you'll be able to push branches directly here and the whole CI will be enabled in your PRs 🙂 |
…r has issue if repetition_penalty is used Signed-off-by: Wang, Yi <[email protected]>
thanks a lot |
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Outdated suggestions cannot be applied.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.
…r has issue if repetition_penalty is used
Fixes # (issue)
it will core dump if set following in text generation example
generation_config.do_sample=True
generation_config.repetition_penalty=0.75
coredump trace like
Traceback (most recent call last):
File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/work/chatbot/inference/generate.py", line 529, in generate_output
return model.generate(
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/work/optimum-habana/optimum/habana/transformers/generation/utils.py", line 627, in generate
return self.sample(
File "/work/optimum-habana/optimum/habana/transformers/generation/utils.py", line 1531, in sample
streamer.put(next_tokens.cpu())
RuntimeError: [Rank:0] FATAL ERROR :: MODULE:PT_BRIDGE syn compile encountered : Graph compile failed. 26 compile time 55892013 ns