Fix runtime errors reported when using long input sequence lengths with LoRA #339
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
| [0] * batch_size * seq_len, | ||
| [0] * batch_size * seq_len, | ||
| ) | ||
| **dict(index_mapping=[0] * batch_size * seq_len, |
There was a problem hiding this comment.
how does introducing dict here affect memory footprint? since we dont have control on when its garbage collected and size grows with batch_size*seq_len
There was a problem hiding this comment.
@michalkuligowski Nothing has changed from existing code, we are still populating the same dataclass (LoRAMapping) as before, **dict simply is to use key, value notation initialization of class members. Regarding memory footprint, this dataclass needs to be available all the time if LoRA is enabled, it is a must have for LoRA operation. Again nothing specific to Gaudi/HPU, this is the way LoRA feature is implemented in vLLM.
hlahkar
approved these changes
Sep 27, 2024
huijjj
pushed a commit
to SqueezeBits/vllm-fork
that referenced
this pull request
Sep 27, 2024
…th LoRA (HabanaAI#339) This PR has following fixes, - Increase size of indices tensors used to maintain multi-lora state information from max_num_batched_tokens to 3*max_num_batched_tokens. This increase is done to provide buffer for padding done in batch & sequence dimensions. - Move logic to remove padding from lora_logits from execute_model() back to Class LogitsProcessorWithLoRA, this is done to fix race condition caused by updating multi-lora state information directly. FIX HabanaAI#237
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Outdated suggestions cannot be applied.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 PR has following fixes,
FIX #237