-
Notifications
You must be signed in to change notification settings - Fork 33
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Signed-off-by: Gaurav Shukla<gashukla@amd.com> Co-authored-by: zjgarvey <zjgarvey@gmail.com> Co-authored-by: kumardeepakamd <123522031+kumardeepakamd@users.noreply.github.com> Co-authored-by: Scott Todd <scott.todd0@gmail.com> Co-authored-by: zjgarvey <47986913+zjgarvey@users.noreply.github.com> Co-authored-by: Andreas Falkenberg <149819731+afalkenberg1@users.noreply.github.com> Co-authored-by: Xida Ren <xida.ren.dev@gmail.com> Co-authored-by: Xida Ren (Cedar) <cedar.ren@gmail.com> Co-authored-by: Gaurav Shukla <gaurav@nod-labs.com> Co-authored-by: Kumar Deepak <kumar@xilinx.com> Co-authored-by: afalkenberg1 <afalkenb@amd.com> Co-authored-by: Phaneesh Barwaria <b.phaneesh@gmail.com> Co-authored-by: Chi_Liu <22491986+AmosLewis@users.noreply.github.com>
- Loading branch information
1 parent
70652b1
commit 5a73d7e
Showing
157 changed files
with
3,532 additions
and
1,065 deletions.
There are no files selected for viewing
This file contains 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
This file contains 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
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,17 @@ | ||
onnx/models/resnet50_vaiq_int8 | ||
pytorch/models/opt-125M | ||
pytorch/models/resnet50 | ||
pytorch/models/opt-1.3b | ||
pytorch/models/beit-base-patch16-224-pt22k-ft22k | ||
pytorch/models/bert-large-uncased | ||
pytorch/models/bge-base-en-v1.5 | ||
pytorch/models/gpt2-xl | ||
pytorch/models/gpt2 | ||
pytorch/models/miniLM-L12-H384-uncased | ||
pytorch/models/opt-350m | ||
pytorch/models/t5-base | ||
pytorch/models/t5-large | ||
pytorch/models/vicuna-13b-v1.3 | ||
pytorch/models/whisper-base | ||
pytorch/models/whisper-medium | ||
pytorch/models/whisper-small |
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,11 +1,42 @@ | ||
onnx/combinations/constant_constantofshape | ||
onnx/operators/add | ||
onnx/operators/CumSum | ||
onnx/operators/Shape | ||
onnx/operators/Pow | ||
onnx/operators/Sigmoid | ||
onnx/operators/add | ||
onnx/operators/gemm | ||
onnx/operators/CumSum | ||
onnx/operators/Pow | ||
onnx/operators/Shape | ||
onnx/operators/Sigmoid | ||
onnx/operators/identity | ||
onnx/operators/relu | ||
onnx/operators/reshape | ||
onnx/operators/reduceprod | ||
onnx/operators/expand | ||
onnx/operators/MatMul | ||
onnx/operators/Mul | ||
onnx/operators/Softmax | ||
onnx/operators/concat | ||
onnx/operators/equal | ||
onnx/operators/flatten | ||
onnx/operators/layernorm | ||
onnx/operators/maxpool | ||
onnx/operators/neg | ||
onnx/operators/gemm2 | ||
pytorch/combinations/mlp | ||
pytorch/models/resnet50 | ||
pytorch/operators/conv2d | ||
pytorch/operators/linear | ||
|
||
pytorch/operators/gridsampler | ||
pytorch/models/opt-125M | ||
pytorch/models/resnet50 | ||
pytorch/models/opt-1.3b | ||
pytorch/models/beit-base-patch16-224-pt22k-ft22k | ||
pytorch/models/bert-large-uncased | ||
pytorch/models/bge-base-en-v1.5 | ||
pytorch/models/gpt2-xl | ||
pytorch/models/gpt2 | ||
pytorch/models/miniLM-L12-H384-uncased | ||
pytorch/models/opt-350m | ||
pytorch/models/t5-base | ||
pytorch/models/t5-large | ||
pytorch/models/vicuna-13b-v1.3 | ||
pytorch/models/whisper-base | ||
pytorch/models/whisper-medium | ||
pytorch/models/whisper-small |
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,10 +1,21 @@ | ||
pytorch/models/t5-large | ||
pytorch/models/bert-large-uncased | ||
pytorch/models/llama2-7b-GPTQ | ||
pytorch/models/opt-350m | ||
pytorch/models/mobilebert-uncased | ||
pytorch/models/opt-1.3b | ||
pytorch/models/whisper-base | ||
pytorch/models/bge-base-en-v1.5 | ||
pytorch/models/miniLM-L12-H384-uncased | ||
pytorch/models/llama2-7b-hf | ||
pytorch/models/t5-base | ||
pytorch/models/bart-large | ||
pytorch/models/vit-base-patch16-224 | ||
pytorch/models/resnet50 | ||
pytorch/models/opt-125M | ||
pytorch/models/beit-base-patch16-224-pt22k-ft22k | ||
pytorch/models/bge-base-en-v1.5 | ||
pytorch/models/whisper-medium | ||
pytorch/models/opt-125M | ||
pytorch/models/opt-125m-gptq | ||
pytorch/models/deit-small-distilled-patch16-224 | ||
pytorch/models/bert-large-uncased | ||
pytorch/models/miniLM-L12-H384-uncased | ||
pytorch/models/opt-1.3b | ||
pytorch/models/opt-350m | ||
pytorch/models/whisper-small | ||
pytorch/models/vicuna-13b-v1.3 |
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,2 +1,4 @@ | ||
# Model artifacts | ||
operators/*/model.onnx | ||
models/*/model.onnx | ||
models/*/model.onnxsignature.json |
82 changes: 82 additions & 0 deletions
82
e2eshark/onnx/combinations/QuantizeToMatMulInteger/model.py
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,82 @@ | ||
# Copyright 2024 Advanced Micro Devices, Inc. | ||
# | ||
# Licensed under the Apache License v2.0 with LLVM Exceptions. | ||
# See https://llvm.org/LICENSE.txt for license information. | ||
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception | ||
|
||
# run.py creates runmodel.py by concatenating this file model.py | ||
# and tools/stubs/onnxmodel.py | ||
|
||
# See https://onnx.ai/onnx/intro/python.html for intro on creating | ||
# onnx model using python onnx API | ||
import numpy, torch, sys | ||
import onnxruntime | ||
from onnx import numpy_helper, TensorProto, save_model | ||
from onnx.helper import make_model, make_node, make_graph, make_tensor_value_info | ||
from onnx.checker import check_model | ||
|
||
# import from e2eshark/tools to allow running in current dir, for run through | ||
# run.pl, commutils is symbolically linked to allow any rundir to work | ||
sys.path.insert(0, "../../../tools/stubs") | ||
from commonutils import E2ESHARK_CHECK_DEF | ||
|
||
# Create an instance of it for this test | ||
E2ESHARK_CHECK = dict(E2ESHARK_CHECK_DEF) | ||
|
||
# Create an input (ValueInfoProto) | ||
X = make_tensor_value_info("X", TensorProto.FLOAT, [2, 4, 5]) | ||
Y = make_tensor_value_info("Y", TensorProto.FLOAT, [5, 3]) | ||
|
||
# Create an output | ||
Z = make_tensor_value_info("Z", TensorProto.INT32, [2, 4, 3]) | ||
|
||
# Create a node (NodeProto) | ||
qlxnode = make_node( | ||
"DynamicQuantizeLinear", ["X"], ["QX", "SX", "ZPX"], "qlxnode" | ||
) | ||
qlynode = make_node( | ||
"DynamicQuantizeLinear", ["Y"], ["QY", "SY", "ZPY"], "qlynode" | ||
) | ||
mminode = make_node( | ||
"MatMulInteger", ["QX", "QY", "ZPX", "ZPY"], ["Z"], "mminode" # node name # inputs # outputs | ||
) | ||
|
||
# Create the graph (GraphProto) | ||
graph = make_graph( | ||
[qlxnode,qlynode, mminode], | ||
"mmigraph", | ||
[X, Y], | ||
[Z], | ||
) | ||
|
||
# Create the model (ModelProto) | ||
onnx_model = make_model(graph) | ||
onnx_model.opset_import[0].version = 19 | ||
|
||
# Save the model | ||
# save_model(onnx_model, "model.onnx") | ||
with open("model.onnx", "wb") as f: | ||
f.write(onnx_model.SerializeToString()) | ||
|
||
session = onnxruntime.InferenceSession("model.onnx", None) | ||
model_input_X = numpy.random.randn(2, 4, 5).astype(numpy.float32) | ||
model_input_Y = numpy.random.randn(5, 3).astype(numpy.float32) | ||
# gets X in inputs[0] and Y in inputs[1] | ||
inputs = session.get_inputs() | ||
# gets Z in outputs[0] | ||
outputs = session.get_outputs() | ||
|
||
model_output = session.run( | ||
[outputs[0].name], | ||
{inputs[0].name: model_input_X, inputs[1].name: model_input_Y}, | ||
) | ||
|
||
# Moving to torch to handle bfloat16 as numpy does not support bfloat16 | ||
E2ESHARK_CHECK["input"] = [ | ||
torch.from_numpy(model_input_X), | ||
torch.from_numpy(model_input_Y), | ||
] | ||
E2ESHARK_CHECK["output"] = [torch.from_numpy(arr) for arr in model_output] | ||
|
||
print("Input:", E2ESHARK_CHECK["input"]) | ||
print("Output:", E2ESHARK_CHECK["output"]) |
This file contains 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
This file contains 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
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,49 @@ | ||
import numpy, torch, sys | ||
import onnxruntime | ||
|
||
# import from e2eshark/tools to allow running in current dir, for run through | ||
# run.pl, commutils is symbolically linked to allow any rundir to work | ||
sys.path.insert(0, "../../../tools/stubs") | ||
from commonutils import E2ESHARK_CHECK_DEF | ||
|
||
# Create an instance of it for this test | ||
E2ESHARK_CHECK = dict(E2ESHARK_CHECK_DEF) | ||
|
||
|
||
# The generated or checked in onnx file must always be called model.onnx | ||
# the tools/stubs/onnxmodel.py is appended to model.py | ||
# to form runmodel.py in the rundirectory which is then taken | ||
# through flow | ||
|
||
|
||
# start an onnxrt session | ||
session = onnxruntime.InferenceSession("model.onnx", None) | ||
|
||
# Even if model is quantized, the inputs and outputs are | ||
# not, so apply float32 | ||
model_input_X = numpy.random.rand(1, 3, 224, 224).astype(numpy.float32) | ||
|
||
# gets X in inputs[0] and Y in inputs[1] | ||
inputs = session.get_inputs() | ||
# gets Z in outputs[0] | ||
outputs = session.get_outputs() | ||
|
||
|
||
model_output = session.run( | ||
[outputs[0].name], | ||
{inputs[0].name: model_input_X}, | ||
)[0] | ||
E2ESHARK_CHECK["input"] = [torch.from_numpy(model_input_X)] | ||
E2ESHARK_CHECK["output"] = [torch.from_numpy(arr) for arr in model_output] | ||
|
||
print("Input:", E2ESHARK_CHECK["input"]) | ||
print("Output:", E2ESHARK_CHECK["output"]) | ||
|
||
# Post process output to do: | ||
# sort(topk(torch.nn.functional.softmax(output, 0), 2)[1])[0] | ||
# Top most probability | ||
# E2ESHARK_CHECK["postprocess"] = [ | ||
# (torch.nn.functional.softmax, [0], False, 0), | ||
# (torch.topk, [2], True, 1), | ||
# (torch.sort, [], True, 0), | ||
# ] |
Oops, something went wrong.