> Thanks @jackwish and @FrozenGene I understand your points.
>
> This can be treated as optimization then. If the input zero point is zero OR
> if the input and output quantization params are same, don't cast, directly
> apply maxpool. Generally, we would like to keep QNN APIs generic. So, if
>
Thanks @jackwish and @FrozenGene I understand your points.
This can be treated as optimization then. If the input zero point is zero OR if
the input and output quantization params are same, don't cast, directly apply
maxpool. Generally, we would like to keep QNN APIs generic. So, if MxNet for
s
> Thanks @jackwish for confirming the python lowering looks good.
>
> For max pooling, we used casting, because we have to subtract the zero point
> from the quantized tensor. That subtract needs to happen in higher precision
> than (u)int8. Correct me if I am wrong.
To me, for Pooling operator
For TFLite model's average_pool / max_pool, which doesn't have
input_zero_point. So, for TFLite, we don't need to subtract zero_point. MXNet
have?
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/
Thanks @jackwish for confirming the python lowering looks good.
For max pooling, we used casting, because we have to subtract the zero point
from the quantized tensor. That subtract needs to happen in higher precision
than (u)int8. Correct me if I am wrong.
--
You are receiving this because yo
I guess the `cast` is not needed in max pooling? Anyway, simply logic for
compile operators looks good.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/issues/3617#issuecomment-517517945
@FrozenGene Can you please review #3627
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/issues/3617#issuecomment-517491952
@jianyuh please act on the review comments @were please
https://docs.tvm.ai/contribute/code_review.html#approve-and-request-changes-explicitly
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/pull/
@ajtulloch please look into the CI error and see if we can fix it.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/pull/3567#issuecomment-517433044
If we have time, we could investigate why we couldn't achieve 252GFlops even
more. Only 73% hardware efficiency means we have much work could dive.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/
@FrozenGene @tqchen @anijain2305 @llyfacebook @were Ping for review.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/pull/3388#issuecomment-517164224
Similar to @anijain2305 's PR (https://github.com/dmlc/tvm/pull/3516),
currently we disable the AVX512 VNNI test in this PR.
Posted the question on tensorize failure in
https://discuss.tvm.ai/t/workaround-for-tensorize-failure/3577.
--
You are receiving this because you are subscribed to this
12 matches
Mail list logo
