Add DecomposeRnnPass for ARM backend (#17139)#17139
Open
apullin wants to merge 2 commits intopytorch:mainfrom
Open
Add DecomposeRnnPass for ARM backend (#17139)#17139apullin wants to merge 2 commits intopytorch:mainfrom
apullin wants to merge 2 commits intopytorch:mainfrom
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17139
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New Failures, 2 Unrelated FailuresAs of commit 973c777 with merge base 7c79395 ( NEW FAILURES - The following jobs have failed:
BROKEN TRUNK - The following jobs failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
This PR needs a
|
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Feb 3, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
---
> Generated by [Confucius Code Assist (CCA)](https://www.internalfb.com/wiki/Confucius/Analect/Shared_Analects/Confucius_Code_Assist_(CCA)/)
[Confucius Session](https://www.internalfb.com/confucius?host=62602.od.fbinfra.net&port=8086&tab=Chat&session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&entry_name=Code+Assist), [Trace](https://www.internalfb.com/confucius?session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&tab=Trace)
Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
from
0fc57ed to
bbb6cbb
Compare
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Feb 3, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
---
> Generated by [Confucius Code Assist (CCA)](https://www.internalfb.com/wiki/Confucius/Analect/Shared_Analects/Confucius_Code_Assist_(CCA)/)
[Confucius Session](https://www.internalfb.com/confucius?host=62602.od.fbinfra.net&port=8086&tab=Chat&session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&entry_name=Code+Assist), [Trace](https://www.internalfb.com/confucius?session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&tab=Trace)
Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
2 times, most recently
from
738855e to
8003c8a
Compare
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Feb 3, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
---
> Generated by [Confucius Code Assist (CCA)](https://www.internalfb.com/wiki/Confucius/Analect/Shared_Analects/Confucius_Code_Assist_(CCA)/)
[Confucius Session](https://www.internalfb.com/confucius?host=62602.od.fbinfra.net&port=8086&tab=Chat&session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&entry_name=Code+Assist), [Trace](https://www.internalfb.com/confucius?session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&tab=Trace)
Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
from
8003c8a to
0a6c163
Compare
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Feb 3, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
---
> Generated by [Confucius Code Assist (CCA)](https://www.internalfb.com/wiki/Confucius/Analect/Shared_Analects/Confucius_Code_Assist_(CCA)/)
[Confucius Session](https://www.internalfb.com/confucius?host=62602.od.fbinfra.net&port=8086&tab=Chat&session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&entry_name=Code+Assist), [Trace](https://www.internalfb.com/confucius?session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&tab=Trace)
Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
2 times, most recently
from
8003c8a to
466c9ab
Compare
Contributor
apullin
force-pushed
the
export-D92059152
branch
from
466c9ab to
3f1d107
Compare
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Feb 3, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
---
> Generated by [Confucius Code Assist (CCA)](https://www.internalfb.com/wiki/Confucius/Analect/Shared_Analects/Confucius_Code_Assist_(CCA)/)
[Confucius Session](https://www.internalfb.com/confucius?host=62602.od.fbinfra.net&port=8086&tab=Chat&session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&entry_name=Code+Assist), [Trace](https://www.internalfb.com/confucius?session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&tab=Trace)
Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Feb 3, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
---
> Generated by [Confucius Code Assist (CCA)](https://www.internalfb.com/wiki/Confucius/Analect/Shared_Analects/Confucius_Code_Assist_(CCA)/)
[Confucius Session](https://www.internalfb.com/confucius?host=62602.od.fbinfra.net&port=8086&tab=Chat&session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&entry_name=Code+Assist), [Trace](https://www.internalfb.com/confucius?session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&tab=Trace)
Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Feb 3, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
---
> Generated by [Confucius Code Assist (CCA)](https://www.internalfb.com/wiki/Confucius/Analect/Shared_Analects/Confucius_Code_Assist_(CCA)/)
[Confucius Session](https://www.internalfb.com/confucius?host=62602.od.fbinfra.net&port=8086&tab=Chat&session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&entry_name=Code+Assist), [Trace](https://www.internalfb.com/confucius?session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&tab=Trace)
Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
from
3f1d107 to
1c44a77
Compare
pytorch-bot bot
pushed a commit
that referenced
this pull request
Feb 6, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
---
> Generated by [Confucius Code Assist (CCA)](https://www.internalfb.com/wiki/Confucius/Analect/Shared_Analects/Confucius_Code_Assist_(CCA)/)
[Confucius Session](https://www.internalfb.com/confucius?host=62602.od.fbinfra.net&port=8086&tab=Chat&session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&entry_name=Code+Assist), [Trace](https://www.internalfb.com/confucius?session_id=e1d1ac52-0014-11f1-9d55-75b7d4e71d8a&tab=Trace)
Differential Revision: D92059152
zingo
added
the
partner: arm
zingo
changed the title
mansnils
requested changes
Feb 6, 2026
apullin
force-pushed
the
export-D92059152
branch
from
1c44a77 to
c6a47fd
Compare
Contributor
Author
|
@pytorchbot label "release notes: feature" |
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 24, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 24, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
2 times, most recently
from
8356482 to
991e144
Compare
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 24, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 24, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 24, 2026
Summary: Pull Request resolved: pytorch#17139 Adds a decomposition pass that transforms aten.rnn_tanh.input and aten.rnn_relu.input into elementary ops supported by TOSA. RNN cell equation per timestep: h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh) where activation is tanh (rnn_tanh) or relu (rnn_relu). Features: - Multi-layer RNN support - Bidirectional RNN support - With/without bias - batch_first support - Both tanh and relu nonlinearities Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
2 times, most recently
from
3591ca5 to
2ba998d
Compare
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 24, 2026
Summary: Pull Request resolved: pytorch#17139 Adds a decomposition pass that transforms aten.rnn_tanh.input and aten.rnn_relu.input into elementary ops supported by TOSA. RNN cell equation per timestep: h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh) where activation is tanh (rnn_tanh) or relu (rnn_relu). Features: - Multi-layer RNN support - Bidirectional RNN support - With/without bias - batch_first support - Both tanh and relu nonlinearities Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
from
2ba998d to
352a04e
Compare
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 24, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
from
352a04e to
948f4f4
Compare
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 24, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 24, 2026
Summary: Pull Request resolved: pytorch#17139 Adds a decomposition pass that transforms aten.rnn_tanh.input and aten.rnn_relu.input into elementary ops supported by TOSA. RNN cell equation per timestep: h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh) where activation is tanh (rnn_tanh) or relu (rnn_relu). Features: - Multi-layer RNN support - Bidirectional RNN support - With/without bias - batch_first support - Both tanh and relu nonlinearities Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
from
948f4f4 to
e3efcf1
Compare
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 24, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
from
e3efcf1 to
c2b44ea
Compare
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 25, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 25, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
force-pushed
the
export-D92059152
branch
2 times, most recently
from
ae79c65 to
dc4781b
Compare
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 25, 2026
Summary: Pull Request resolved: pytorch#17139 Adds a decomposition pass that transforms aten.rnn_tanh.input and aten.rnn_relu.input into elementary ops supported by TOSA. RNN cell equation per timestep: h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh) where activation is tanh (rnn_tanh) or relu (rnn_relu). Features: - Multi-layer RNN support - Bidirectional RNN support - With/without bias - batch_first support - Both tanh and relu nonlinearities Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 25, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 25, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 26, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 26, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
apullin
pushed a commit
to apullin/executorch
that referenced
this pull request
Mar 26, 2026
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
- Multi-layer RNN support
- Bidirectional RNN support
- With/without bias
- batch_first support
- Both tanh and relu nonlinearities
Differential Revision: D92059152
Summary:
Adds a decomposition pass that transforms aten.gru.input into elementary
ops supported by TOSA (matmul, sigmoid, tanh, mul, add, slice, cat).
GRU cell equations per timestep:
r_t = sigmoid(x_t @ W_ir.T + b_ir + h_{t-1} @ W_hr.T + b_hr)
z_t = sigmoid(x_t @ W_iz.T + b_iz + h_{t-1} @ W_hz.T + b_hz)
n_t = tanh(x_t @ W_in.T + b_in + r_t * (h_{t-1} @ W_hn.T + b_hn))
h_t = n_t + z_t * (h_{t-1} - n_t)
Features:
- Multi-layer GRU support
- Bidirectional GRU support
- With/without bias
- batch_first support
- Batched gate computation (2 mm ops per timestep instead of 6)
Differential Revision: D92058313
Summary: Pull Request resolved: pytorch#17139 Adds a decomposition pass that transforms aten.rnn_tanh.input and aten.rnn_relu.input into elementary ops supported by TOSA. RNN cell equation per timestep: h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh) where activation is tanh (rnn_tanh) or relu (rnn_relu). Features: - Multi-layer RNN support - Bidirectional RNN support - With/without bias - batch_first support - Both tanh and relu nonlinearities Differential Revision: D92059152
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Summary:
Adds a decomposition pass that transforms aten.rnn_tanh.input and
aten.rnn_relu.input into elementary ops supported by TOSA.
RNN cell equation per timestep:
h_t = activation(x_t @ W_ih.T + b_ih + h_{t-1} @ W_hh.T + b_hh)
where activation is tanh (rnn_tanh) or relu (rnn_relu).
Features:
Differential Revision: D92059152