fix: docs + new dep group

[narendasan]

Description

Fix documentation building

Fixes # (issue)

Type of change

Please delete options that are not relevant and/or add your own.

• Bug fix (non-breaking change which fixes an issue)

Checklist:

• My code follows the style guidelines of this project (You can use the linters)
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas and hacks
• I have made corresponding changes to the documentation
• I have added tests to verify my fix or my feature
• New and existing unit tests pass locally with my changes
• I have added the relevant labels to my PR in so that relevant reviewers are notified

[github-actions]

There are some changes that do not conform to Python style guidelines:

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/compile_with_dynamic_inputs.py	2026-01-29 19:50:57.564183+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/compile_with_dynamic_inputs.py	2026-01-29 19:51:30.211201+00:00
@@ -24,10 +24,11 @@
logging.basicConfig(level=logging.DEBUG)

torch.manual_seed(0)

# %%
+

# Define a model with expand and reshape operations
# This is a simplified Vision Transformer pattern with:
# - A learnable class token that needs to expand to match batch size
# - A QKV projection followed by reshaping for multi-head attention

[github-actions]

There are some changes that do not conform to Python style guidelines:

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/compile_with_dynamic_inputs.py	2026-01-29 19:52:54.555414+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/compile_with_dynamic_inputs.py	2026-01-29 19:53:26.945609+00:00
@@ -24,10 +24,11 @@
logging.basicConfig(level=logging.DEBUG)

torch.manual_seed(0)

# %%
+

# Define a model with expand and reshape operations
# This is a simplified Vision Transformer pattern with:
# - A learnable class token that needs to expand to match batch size
# - A QKV projection followed by reshaping for multi-head attention

[github-actions]

There are some changes that do not conform to Python style guidelines:

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/compile_with_dynamic_inputs.py	2026-01-29 19:54:57.305479+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/compile_with_dynamic_inputs.py	2026-01-29 19:55:29.533323+00:00
@@ -24,10 +24,11 @@
logging.basicConfig(level=logging.DEBUG)

torch.manual_seed(0)

# %%
+

# Define a model with expand and reshape operations
# This is a simplified Vision Transformer pattern with:
# - A learnable class token that needs to expand to match batch size
# - A QKV projection followed by reshaping for multi-head attention

[github-actions]

There are some changes that do not conform to Python style guidelines:

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/autocast_example.py	2026-01-29 19:57:56.468654+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/autocast_example.py	2026-01-29 19:58:29.240203+00:00
@@ -104,21 +104,19 @@
should_be_fp16 = [
    autocast_outs[8],
]
should_be_bf16 = [autocast_outs[3], autocast_outs[4], autocast_outs[6]]

-assert all(a.dtype == torch.float32 for a in should_be_fp32), (
-    "Some Autocast outputs are not float32!"
-)
-assert all(a.dtype == torch.float16 for a in should_be_fp16), (
-    "Some Autocast outputs are not float16!"
-)
-assert all(a.dtype == torch.bfloat16 for a in should_be_bf16), (
-    "Some Autocast outputs are not bfloat16!"
-)
+assert all(
+    a.dtype == torch.float32 for a in should_be_fp32
+), "Some Autocast outputs are not float32!"
+assert all(
+    a.dtype == torch.float16 for a in should_be_fp16
+), "Some Autocast outputs are not float16!"
+assert all(
+    a.dtype == torch.bfloat16 for a in should_be_bf16
+), "Some Autocast outputs are not bfloat16!"
for i, (a, w) in enumerate(zip(autocast_outs, pytorch_outs)):
    assert torch.allclose(
        a.to(torch.float32), w.to(torch.float32), atol=1e-2, rtol=1e-2
-    ), (
-        f"Autocast and Pytorch outputs do not match! autocast_outs[{i}] = {a}, pytorch_outs[{i}] = {w}"
-    )
+    ), f"Autocast and Pytorch outputs do not match! autocast_outs[{i}] = {a}, pytorch_outs[{i}] = {w}"
print("All dtypes and values match!")
--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/refit_engine_example.py	2026-01-29 19:57:56.468654+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/refit_engine_example.py	2026-01-29 19:58:29.373306+00:00
@@ -103,13 +103,13 @@
    expected_outputs, refitted_outputs = (
        exp_program2.module()(*inputs),
        new_trt_gm(*inputs),
    )
    for expected_output, refitted_output in zip(expected_outputs, refitted_outputs):
-        assert torch.allclose(expected_output, refitted_output, 1e-2, 1e-2), (
-            "Refit Result is not correct. Refit failed"
-        )
+        assert torch.allclose(
+            expected_output, refitted_output, 1e-2, 1e-2
+        ), "Refit Result is not correct. Refit failed"

print("Refit successfully!")

# %%
#
--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/nvrtc_aot_plugin.py	2026-01-29 19:57:56.468654+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/nvrtc_aot_plugin.py	2026-01-29 19:58:29.417137+00:00
@@ -237,10 +237,10 @@

        print("Running inference with compiled model...")
        with torch.no_grad():
            for i in range(10):
                res = model_trt(input)
-                assert torch.allclose(res, model(input), rtol=1e-2, atol=1e-2), (
-                    "Results do not match!"
-                )
+                assert torch.allclose(
+                    res, model(input), rtol=1e-2, atol=1e-2
+                ), "Results do not match!"

    print("Inference successful!")
--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/mutable_torchtrt_module_example.py	2026-01-29 19:57:56.468654+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/mutable_torchtrt_module_example.py	2026-01-29 19:58:29.464922+00:00
@@ -55,13 +55,13 @@
# Check the output
# The refit happens while you call the mutable module again.
with torch.no_grad():
    expected_outputs, refitted_outputs = model2(*inputs), mutable_module(*inputs)
for expected_output, refitted_output in zip(expected_outputs, refitted_outputs):
-    assert torch.allclose(expected_output, refitted_output, 1e-2, 1e-2), (
-        "Refit Result is not correct. Refit failed"
-    )
+    assert torch.allclose(
+        expected_output, refitted_output, 1e-2, 1e-2
+    ), "Refit Result is not correct. Refit failed"

print("Refit successfully!")

# %%
# Saving Mutable Torch TensorRT Module

[lanluo-nvidia]

LGTM