-
Notifications
You must be signed in to change notification settings - Fork 21.4k
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
topk, bmm, max ops - Multiple dispatch failed for 'torch.ops.aten.size'; all __torch_dispatch__ handlers returned NotImplemented: #122772
Labels
module: dynamic shapes
module: fakeTensor
module: pt2-dispatcher
PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,
oncall: pt2
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Comments
Yeah there's some sort of problem here. It's also the reason why test_make_fx_symbolic_exhaustive_nn_functional_fractional_max_pool3d_cpu_float32 is xfailed |
ezyang
added
module: fakeTensor
module: pt2-dispatcher
PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,
labels
Mar 28, 2024
yf225
added
the
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
label
Mar 30, 2024
What looks like is happening is that we're attempting to run the underlying meta for topk (eg), and somehow we're redispatching to fake tensor mode (!!!) |
OnlyFor
pushed a commit
to OnlyFor/pytorch
that referenced
this issue
Apr 24, 2024
Fixes pytorch#122772 Signed-off-by: Edward Z. Yang <ezyang@meta.com> ghstack-source-id: 88d5a17ea80313d8a506616ceb618a97eec7f2a4 Pull Request resolved: pytorch#124760
alat-rights
pushed a commit
to alat-rights/pytorch
that referenced
this issue
Apr 26, 2024
…ypes from toInt/etc in IValue (pytorch#124760) Fixes pytorch#122772 Signed-off-by: Edward Z. Yang <ezyang@meta.com> Pull Request resolved: pytorch#124760 Approved by: https://github.com/albanD, https://github.com/eellison
carmocca
pushed a commit
to carmocca/pytorch
that referenced
this issue
Apr 29, 2024
…ypes from toInt/etc in IValue (pytorch#124760) Fixes pytorch#122772 Signed-off-by: Edward Z. Yang <ezyang@meta.com> Pull Request resolved: pytorch#124760 Approved by: https://github.com/albanD, https://github.com/eellison
andoorve
pushed a commit
to andoorve/pytorch
that referenced
this issue
May 1, 2024
…ypes from toInt/etc in IValue (pytorch#124760) Fixes pytorch#122772 Signed-off-by: Edward Z. Yang <ezyang@meta.com> Pull Request resolved: pytorch#124760 Approved by: https://github.com/albanD, https://github.com/eellison
pytorch-bot bot
pushed a commit
that referenced
this issue
May 3, 2024
…ypes from toInt/etc in IValue (#124760) Fixes #122772 Signed-off-by: Edward Z. Yang <ezyang@meta.com> Pull Request resolved: #124760 Approved by: https://github.com/albanD, https://github.com/eellison
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
module: dynamic shapes
module: fakeTensor
module: pt2-dispatcher
PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,
oncall: pt2
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
🐛 Describe the bug
Following error is observed for out variants of topk, bmm and max ops:
Multiple dispatch failed for 'torch.ops.aten.size'; all torch_dispatch handlers returned NotImplemented:
Error logs
Minified repro
topk
bmm
max
Versions
cc @ezyang @msaroufim @bdhirsh @anijain2305 @zou3519 @chauhang @eellison
The text was updated successfully, but these errors were encountered: