-
Notifications
You must be signed in to change notification settings - Fork 3.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add bfloat16 to all relevant ops #3842
Comments
FYI @gramalingam, @souptc. |
Just noticed also that |
Makes sense. Looks like an oversight. We should add the missing bfloat16 type to all such ops. Would be nice to find all such ops in one go! (Eg., we had to do this for Pow and Where previously I think.) |
Here is a list of other ops that may be missing bfloat16: acos, acosh, asin, asinh, atan, atanh, averagepool, bernoulli, celu, concatfromsequence, constantofshape, conv, convtranspose, cos, cosh, dequantizelinear, det, dynamicquantizelinear, einsum, eyelike, globalaveragepool, globalpool, globalmaxpool, gru, hardsigmoid, hardswish, if, instancenormalization, isinf, leakyrelu, loop, lstm, maxpool, maxroipool, maxunpool, multinomial, negativeloglikelihoodloss, nonmaxsuppression, onehot, optional, optionalgetelement, optionalhaselement, prelu, resize, reversesequence, rnn, roialign, round, scan, scatterlements, selu, sequenceat, sequenceconstruct, sequenceempty, sequenceerase, sequenceinsert, sequencelength, shrink, sin, sinh, softplus, softsign, splittosequence, thresholdedrelu, topk, unique. |
Adding a note to clarify that bfloat16 was added for a few selected ops, not all of the ops identified above as missing bfloat16. So, this issue is only partially closed. |
I did not close this issue... I think it was closed becuase the PR got merged. Reopening the issue to continue to track the rest of the ops. Per our discussion will remove the 1.11 milestone tag |
#4051 Another fresh bfloat request for Conv op. |
I guess it has not been fully completed yet. Let me reopen it for tracking. |
We can add fp8 now too |
#6071 is a duplicate - and more specific case for Conv-11 which has float16 but not bfloat16 support |
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Conversion to/from 21<->22 also implemented Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Conversion to/from 21<->22 also implemented Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Conversion to/from 21<->22 also implemented Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Conversion to/from 21<->22 also implemented Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Conversion to/from 21<->22 also implemented Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Conversion to/from 21<->22 also implemented Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Conversion to/from 21<->22 also implemented Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Conversion to/from 21<->22 also implemented Fixes onnx#3842 Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Reland #6079 Fixes #3842 Fixes #6071 Fixes #4051 @gramalingam @justinchuby FYI Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
Reland onnx#6079 Fixes onnx#3842 Fixes onnx#6071 Fixes onnx#4051 @gramalingam @justinchuby FYI Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com> Signed-off-by: isdanni <leedanni@gmail.com>
Reland onnx#6079 Fixes onnx#3842 Fixes onnx#6071 Fixes onnx#4051 @gramalingam @justinchuby FYI Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com> Signed-off-by: Ganesan Ramalingam <grama@microsoft.com>
Bug Report
Is the issue related to model conversion?
No.
Looks like an oversight, as it's inconsistent with both
Less
andEqual
which support bfloat16 but their combination does not, especially givenLessOrEqual
can be implemented as an aggregate operator ("function") of those two. The same applies toGreaterOrEqual
.Describe the bug
LessOrEqual and GreaterOrEqual should support bfloat16. Pertinent PR #2770.
System information
The text was updated successfully, but these errors were encountered: