[ONNX] Export module as function #105618
Closed
[ONNX] Export module as function #105618
Conversation
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
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/105618
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 99b3cee: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
BowenBao
commented
Jul 19, 2023
[ghstack-poisoned]
|
Is the pass always turned on? Do we expect the current ort dev build to execute without errors when users want to test the new exporter? |
justinchuby
reviewed
Jul 19, 2023
justinchuby
reviewed
Jul 19, 2023
Yes. Yes for PT 2.1, and no for now. |
Introduce `Modularize` pass that analyzes the flat `fx.GraphModule` and creates nested layers of sub `fx.GraphModule`s along with the `call_module` fx nodes that invokes them. The analysis is done on the meta data "nn_module_stack", which captures the `nn.Module` each flat `fx.Node` belongs to. `FxOnnxInterpreter` is updated to support `call_module`. The related sub module linked by `node.target` is exported as an ONNX model local function. The `call_module` node itself is exported as an ONNX node, associated with the ONNX model local function by op_type. [ghstack-poisoned]
…function" Introduce `Modularize` pass that analyzes the flat `fx.GraphModule` and creates nested layers of sub `fx.GraphModule`s along with the `call_module` fx nodes that invokes them. The analysis is done on the meta data "nn_module_stack", which captures the `nn.Module` each flat `fx.Node` belongs to. `FxOnnxInterpreter` is updated to support `call_module`. The related sub module linked by `node.target` is exported as an ONNX model local function. The `call_module` node itself is exported as an ONNX node, associated with the ONNX model local function by op_type. [ghstack-poisoned]
Introduce `Modularize` pass that analyzes the flat `fx.GraphModule` and creates nested layers of sub `fx.GraphModule`s along with the `call_module` fx nodes that invokes them. The analysis is done on the meta data "nn_module_stack", which captures the `nn.Module` each flat `fx.Node` belongs to. `FxOnnxInterpreter` is updated to support `call_module`. The related sub module linked by `node.target` is exported as an ONNX model local function. The `call_module` node itself is exported as an ONNX node, associated with the ONNX model local function by op_type. [ghstack-poisoned]
justinchuby
approved these changes
Jul 20, 2023
titaiwangms
reviewed
Jul 20, 2023
| @@ -171,6 +172,10 @@ | |||
| "addmm", dtypes=onnx_test_common.BOOL_TYPES, | |||
| reason=onnx_test_common.reason_onnx_does_not_support("Addmm") | |||
| ), | |||
| xfail( | |||
| "all", | |||
| reason="[PostInline][ORT][ShapeInferenceError] axis must be in [-rank, rank-1]. input rank was 0" | |||
There was a problem hiding this comment.
Haven't looked closely, likely due to inliner and unrelated to module as function.
Suspect related to inlining exposing the inner if op that conditions on input rank.
Introduce `Modularize` pass that analyzes the flat `fx.GraphModule` and creates nested layers of sub `fx.GraphModule`s along with the `call_module` fx nodes that invokes them. The analysis is done on the meta data "nn_module_stack", which captures the `nn.Module` each flat `fx.Node` belongs to. `FxOnnxInterpreter` is updated to support `call_module`. The related sub module linked by `node.target` is exported as an ONNX model local function. The `call_module` node itself is exported as an ONNX node, associated with the ONNX model local function by op_type. [ghstack-poisoned]
Introduce `Modularize` pass that analyzes the flat `fx.GraphModule` and creates nested layers of sub `fx.GraphModule`s along with the `call_module` fx nodes that invokes them. The analysis is done on the meta data "nn_module_stack", which captures the `nn.Module` each flat `fx.Node` belongs to. `FxOnnxInterpreter` is updated to support `call_module`. The related sub module linked by `node.target` is exported as an ONNX model local function. The `call_module` node itself is exported as an ONNX node, associated with the ONNX model local function by op_type. [ghstack-poisoned]
Introduce `Modularize` pass that analyzes the flat `fx.GraphModule` and creates nested layers of sub `fx.GraphModule`s along with the `call_module` fx nodes that invokes them. The analysis is done on the meta data "nn_module_stack", which captures the `nn.Module` each flat `fx.Node` belongs to. `FxOnnxInterpreter` is updated to support `call_module`. The related sub module linked by `node.target` is exported as an ONNX model local function. The `call_module` node itself is exported as an ONNX node, associated with the ONNX model local function by op_type. [ghstack-poisoned]
Introduce `Modularize` pass that analyzes the flat `fx.GraphModule` and creates nested layers of sub `fx.GraphModule`s along with the `call_module` fx nodes that invokes them. The analysis is done on the meta data "nn_module_stack", which captures the `nn.Module` each flat `fx.Node` belongs to. `FxOnnxInterpreter` is updated to support `call_module`. The related sub module linked by `node.target` is exported as an ONNX model local function. The `call_module` node itself is exported as an ONNX node, associated with the ONNX model local function by op_type. [ghstack-poisoned]
…tion" Introduce `Modularize` pass that analyzes the flat `fx.GraphModule` and creates nested layers of sub `fx.GraphModule`s along with the `call_module` fx nodes that invokes them. The analysis is done on the meta data "nn_module_stack", which captures the `nn.Module` each flat `fx.Node` belongs to. `FxOnnxInterpreter` is updated to support `call_module`. The related sub module linked by `node.target` is exported as an ONNX model local function. The `call_module` node itself is exported as an ONNX node, associated with the ONNX model local function by op_type. [ghstack-poisoned]
Introduce `Modularize` pass that analyzes the flat `fx.GraphModule` and creates nested layers of sub `fx.GraphModule`s along with the `call_module` fx nodes that invokes them. The analysis is done on the meta data "nn_module_stack", which captures the `nn.Module` each flat `fx.Node` belongs to. `FxOnnxInterpreter` is updated to support `call_module`. The related sub module linked by `node.target` is exported as an ONNX model local function. The `call_module` node itself is exported as an ONNX node, associated with the ONNX model local function by op_type. [ghstack-poisoned]
justinchuby
reviewed
Jul 24, 2023
Introduce `Modularize` pass that analyzes the flat `fx.GraphModule` and creates nested layers of sub `fx.GraphModule`s along with the `call_module` fx nodes that invokes them. The analysis is done on the meta data "nn_module_stack", which captures the `nn.Module` each flat `fx.Node` belongs to. `FxOnnxInterpreter` is updated to support `call_module`. The related sub module linked by `node.target` is exported as an ONNX model local function. The `call_module` node itself is exported as an ONNX node, associated with the ONNX model local function by op_type. [ghstack-poisoned]
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Stack from ghstack (oldest at bottom):
Introduce
Modularizepass that analyzes the flatfx.GraphModuleand creates nestedlayers of sub
fx.GraphModules along with thecall_modulefx nodes that invokes them.The analysis is done on the meta data "nn_module_stack", which captures the
nn.Moduleeach flat
fx.Nodebelongs to.FxOnnxInterpreteris updated to supportcall_module. The related sub module linkedby
node.targetis exported as an ONNX model local function. Thecall_modulenode itselfis exported as an ONNX node, associated with the ONNX model local function by op_type.