Closed jiqing-feng closed 1 week ago
Related to https://github.com/huggingface/transformers/pull/31342 but I dont quite get your changes - what exactly does it fix? When I tested all the pipelines in fp16 none of them had issues outputting logits
Related to #31342 but I dont quite get your changes - what exactly does it fix? When I tested all the pipelines in fp16 none of them had issues outputting logits
Hi @aliencaocao , FP16 works fine but BF16 is not acceptable for numpy, you can see:
Hi @SunMarc. I have fixed all your comments; please review them. BTW, the failed tests are due to the connection error, not related to my changes.
Hi @amyeroberts , would you please review this PR? Thx!
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.
Hi @amyeroberts . I have passed all tests, do you mind take a review and merge it? Thx!
Hi @amyeroberts . This PR should be ready to merge, please take a review, thx!
Hi @jiqing-feng, thanks for opening this PR! I'll get to reviewing it soon, but will likely be in a few days.
Hi @amyeroberts . Do you mind reviewing this PR? Thx.
Hi @amyeroberts . Do you think it could be merged?
@amyeroberts , could you help review this PR? Thx.
@SunMarc , do you have a suggestion any other people from HF can help review and merge this PR? Seems @amyeroberts has no bandwidth on this these serval months. Thx.
Sorry for the delay @yao-matrix!
@Rocketknight1 is managing the pipeline; Matt, would you mind reviewing this PR when you have a second?
Overall this PR seems good to me! However, I prefer
if outputs.dtype in (torch.bfloat16, torch.float16)
rather thanif outputs.dtype == torch.bfloat16
, so we can catchfloat16
as well.Other than that, I'm happy with it!
Hi @Rocketknight1 , thanks for your review, I have fixed it by your comments.
Hi @Rocketknight1 , do you mind helping to re-run the tests? Thx.
Hi @jiqing-feng, another PR at #33554 touched the same files. I'm sorry - I didn't realize that it was doing the same thing as this PR! That PR has been merged, so I've merged this PR with the code there to avoid conflicts.
@jiqing-feng tests pass now and this looks good - are you okay for us to merge it?
Also cc @LysandreJik for final review, but no rush!
@jiqing-feng tests pass now and this looks good - are you okay for us to merge it?
Yes, please.
Hi @amyeroberts @Narsil .
As the previous PR #31444 mentioned, it could enable low-precision pipelines by converting the outputs to
float()
. I followed the codes in here. Do you mind taking a review? Thx!