Fix max allowed lengths for prompts larger than 4096 #74
Conversation
This file contains hidden or 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
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
JRosenkranz
reviewed
Jul 8, 2025
aiu_fms_testing_utils/utils/paged.py
Outdated
| @@ -27,6 +27,7 @@ def adjust_inputs_to_batch(input_ids: torch.Tensor, **extra_kwargs): | |||
| def generate( | |||
| model: Union[Callable, torch.nn.Module], | |||
| input_ids: torch.Tensor, | |||
| max_seq_len: int = 4096, | |||
There was a problem hiding this comment.
Do we anticipate this getting used? or is it just a placeholder to grab the max_seq_len param if passed to fms generate?
There was a problem hiding this comment.
this is to match the signature between both generate() calls and avoid errors yes
There was a problem hiding this comment.
We may just want this to be part of the attention_specific_kwargs in the inference and warmup
JRosenkranz
reviewed
Jul 10, 2025
| @@ -53,6 +53,7 @@ def warmup_model( | |||
| generate( | |||
| model, | |||
| _warmup_input_ids, | |||
| max_seq_len=_warmup_input_ids.shape[1] + max_new_tokens, | |||
There was a problem hiding this comment.
could we just add this to the attention_specific_kwargs in line 32? this way we don't need to change the signature of paged generate.
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
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Outdated suggestions cannot be applied.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.
This takes cares of an oversight that prevented prompts longer than 4k from being run with generate()