Enabled BnB NF4 inference on Gaudi #1457
Draft
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
vivekgoe
requested changes
Jun 19, 2025
rsshaik1
force-pushed
the
tests_bnb
branch
2 times, most recently
from
2cc1fdb to
aac9d3f
Compare
rsshaik1
changed the title
vivekgoe
requested changes
Jun 23, 2025
| models_pre_quant_4bit_to_test = [("hugging-quants/Meta-Llama-3.1-8B-BNB-NF4", | ||
| "read_pre-quantized_4-bit_NF4_opt_model")] | ||
|
|
||
| models_pre_quant_8bit_to_test = [ |
There was a problem hiding this comment.
Since we are not testing for 8-bit quant support for now, therefore we can remove these lines.
| model_name, True) | ||
|
|
||
|
|
||
| @pytest.mark.skipif(torch.cuda.device_count() < 2, |
| ) | ||
|
|
||
|
|
||
| @pytest.mark.skipif(torch.cuda.device_count() < 2, |
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Outdated suggestions cannot be applied.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 adds inference tests for bitsandbytes NF4 quantization on Gaudi, supporting both pre-quantized models and models that are quantized at runtime.