From af9d60c985f847595e2bf123ac534fdcef3a5728 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Dani=C3=ABl=20de=20Kok?= Date: Wed, 5 Jun 2024 14:49:15 +0200 Subject: [PATCH] Fix GPTQWeight import (#2020) # What does this PR do? Fix stray import. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- server/text_generation_server/layers/gptq/exllama.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/server/text_generation_server/layers/gptq/exllama.py b/server/text_generation_server/layers/gptq/exllama.py index 4875af38..f27666b7 100644 --- a/server/text_generation_server/layers/gptq/exllama.py +++ b/server/text_generation_server/layers/gptq/exllama.py @@ -1,4 +1,4 @@ -from text_generation_server.utils.weights import GPTQWeight +from text_generation_server.layers.gptq import GPTQWeight import torch from exllama_kernels import make_q4, q4_matmul, prepare_buffers, set_tuning_params