Skip to content

[executorch][nvidia][tensorrt][21/n] Add comparison and slice converters #17932

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.

Sign up for GitHub

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

Open
shoumikhin wants to merge 1 commit into
base: gh/shoumikhin/46/base
Choose a base branch
from
Open

[executorch][nvidia][tensorrt][21/n] Add comparison and slice converters #17932

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions backends/nvidia/tensorrt/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -162,6 +162,23 @@ with open("model_tensorrt.pte", "wb") as f:
| Elementwise | add, sub, mul, div, mm, relu |
| Reshape | view, reshape, squeeze, unsqueeze, permute, contiguous, clone |

## Supported Operations

| Category | Operations |
|----------|-----------|
| Elementwise | add, sub, mul, div, floor_divide, rsub |
| Matrix | mm, addmm, bmm, linear |
| Convolution | conv2d |
| Normalization | batch_norm, layer_norm |
| Pooling | avg_pool2d, adaptive_avg_pool2d |
| Activations | relu, sigmoid, tanh, gelu, silu, hardswish, hardsigmoid, softmax, log_softmax, clamp |
| Reshape | view, reshape, squeeze, unsqueeze, permute, transpose, flatten, unflatten, contiguous, clone |
| Reduction | mean, any |
| Concat/Split | cat, split, chunk, stack |
| Comparison | eq, ne, lt, le, gt, ge, where, logical_not |
| Slicing | slice, select, index |
| Other | embedding, expand, repeat, upsample, pixel_shuffle, scaled_dot_product_attention, full |

## Jetson Deployment

### Performance Tuning
Expand Down
2 changes: 2 additions & 0 deletions backends/nvidia/tensorrt/converters/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
Expand All @@ -13,6 +13,7 @@
from executorch.backends.nvidia.tensorrt.converters import batch_norm # noqa: F401
from executorch.backends.nvidia.tensorrt.converters import bmm # noqa: F401
from executorch.backends.nvidia.tensorrt.converters import clamp # noqa: F401
from executorch.backends.nvidia.tensorrt.converters import comparison # noqa: F401
from executorch.backends.nvidia.tensorrt.converters import concat # noqa: F401
from executorch.backends.nvidia.tensorrt.converters import conv2d # noqa: F401
from executorch.backends.nvidia.tensorrt.converters import dim_order_ops # noqa: F401
Expand All @@ -31,6 +32,7 @@
from executorch.backends.nvidia.tensorrt.converters import relu # noqa: F401
from executorch.backends.nvidia.tensorrt.converters import reshape # noqa: F401
from executorch.backends.nvidia.tensorrt.converters import sdpa # noqa: F401
from executorch.backends.nvidia.tensorrt.converters import slice # noqa: F401
from executorch.backends.nvidia.tensorrt.converters import sub # noqa: F401
from executorch.backends.nvidia.tensorrt.converters import upsample # noqa: F401

Expand Down
Loading
Loading