Skip to content
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

[Doc] Fix doc build error in e2e_opt_model.py #17319

Merged
merged 1 commit into from
Sep 2, 2024
Merged

[Doc] Fix doc build error in e2e_opt_model.py #17319

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
63 changes: 31 additions & 32 deletions docs/how_to/tutorials/e2e_opt_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,6 @@
# PyTorch.

import os
import sys
import numpy as np
import torch
from torch import fx
Expand Down Expand Up @@ -101,39 +100,39 @@

# Skip running in CI environment
IS_IN_CI = os.getenv("CI", "") == "true"
if IS_IN_CI:
sys.exit(0)

with target:
mod = tvm.ir.transform.Sequential(
[
# Convert BatchNorm into a sequence of simpler ops for fusion
relax.transform.DecomposeOpsForInference(),
# Canonicalize the bindings
relax.transform.CanonicalizeBindings(),
# Run default optimization pipeline
relax.get_pipeline("zero"),
# Tune the model and store the log to database
relax.transform.MetaScheduleTuneIRMod({}, work_dir, TOTAL_TRIALS),
# Apply the database
relax.transform.MetaScheduleApplyDatabase(work_dir),
]
)(mod)

# Only show the main function
mod["main"].show()
if not IS_IN_CI:
with target:
mod = tvm.ir.transform.Sequential(
[
# Convert BatchNorm into a sequence of simpler ops for fusion
relax.transform.DecomposeOpsForInference(),
# Canonicalize the bindings
relax.transform.CanonicalizeBindings(),
# Run default optimization pipeline
relax.get_pipeline("zero"),
# Tune the model and store the log to database
relax.transform.MetaScheduleTuneIRMod({}, work_dir, TOTAL_TRIALS),
# Apply the database
relax.transform.MetaScheduleApplyDatabase(work_dir),
]
)(mod)

# Only show the main function
mod["main"].show()

######################################################################
# Build and Deploy
# ----------------
# Finally, we build the optimized model and deploy it to the target device.

ex = relax.build(mod, target="cuda")
dev = tvm.device("cuda", 0)
vm = relax.VirtualMachine(ex, dev)
# Need to allocate data and params on GPU device
gpu_data = tvm.nd.array(np.random.rand(1, 3, 224, 224).astype("float32"), dev)
gpu_params = [tvm.nd.array(p, dev) for p in params["main"]]
gpu_out = vm["main"](gpu_data, *gpu_params).numpy()

print(gpu_out.shape)
# We skip this step in the CI environment.

if not IS_IN_CI:
ex = relax.build(mod, target="cuda")
dev = tvm.device("cuda", 0)
vm = relax.VirtualMachine(ex, dev)
# Need to allocate data and params on GPU device
gpu_data = tvm.nd.array(np.random.rand(1, 3, 224, 224).astype("float32"), dev)
gpu_params = [tvm.nd.array(p, dev) for p in params["main"]]
gpu_out = vm["main"](gpu_data, *gpu_params).numpy()

print(gpu_out.shape)
Loading