Qwen nan fix #522
Merged
Qwen nan fix #522
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
…vllm, so we need to pad intermediate_size from 29568 to 29696. But after padding, the nan problem occurs again. This commit fix it.
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Outdated suggestions cannot be applied.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.
After quantization, Qwen2-72B can not inference using multi gpu with vllm, so we need to pad intermediate_size from 29568 to 29696 with zeros. But after padding, the nan problem occurs again. This commit fix it.
The details can be found in QwenLM/Qwen2.5#578, it's found in GPTQ, but also occurs in AWQ.