Benchmark: Model benchmark - add option to exclude data copy time in model benchmarks

[yukirora]

Description
add option to exclude data copy time in model benchmarks.

Major Revision

• add an option --exclude_copy_time
• move start time after data copy finish in measured time

[codecov]

Codecov Report

❌ Patch coverage is 52.00000% with 12 lines in your changes missing coverage. Please review.
✅ Project coverage is 85.97%. Comparing base (ad8e014) to head (761b973).
⚠️ Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
...rbench/benchmarks/model_benchmarks/pytorch_bert.py	50.00%	2 Missing ⚠️
...erbench/benchmarks/model_benchmarks/pytorch_cnn.py	50.00%	2 Missing ⚠️
...rbench/benchmarks/model_benchmarks/pytorch_gpt2.py	50.00%	2 Missing ⚠️
...bench/benchmarks/model_benchmarks/pytorch_llama.py	50.00%	2 Missing ⚠️
...rbench/benchmarks/model_benchmarks/pytorch_lstm.py	50.00%	2 Missing ⚠️
...enchmarks/model_benchmarks/pytorch_mixtral_impl.py	50.00%	2 Missing ⚠️

❌ Your patch status has failed because the patch coverage (52.00%) is below the target coverage (80.00%). You can increase the patch coverage or adjust the target coverage.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #734      +/-   ##
==========================================
- Coverage   86.08%   85.97%   -0.12%     
==========================================
  Files         102      102              
  Lines        7553     7578      +25     
==========================================
+ Hits         6502     6515      +13     
- Misses       1051     1063      +12     

Flag	Coverage Δ
cpu-python3.10-unit-test	71.05% <20.00%> (-0.18%)	⬇️
cpu-python3.12-unit-test	71.05% <20.00%> (-0.18%)	⬇️
cpu-python3.7-unit-test	70.49% <20.00%> (-0.17%)	⬇️
cuda-unit-test	83.86% <52.00%> (-0.11%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[Copilot]

Pull Request Overview

This PR adds a new --no_copy option to model benchmarks that allows excluding data copy time from benchmark measurements. When enabled, the timing measurement starts after the GPU data copy operation is completed rather than before it.

• Added a new command-line argument --no_copy to exclude data copy time from benchmarks
• Modified timing logic in all model benchmark implementations to optionally start timing after GPU memory transfers
• Updated test documentation to reflect the new option

Reviewed Changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 1 comment.

File	Description
model_base.py	Adds the new --no_copy command-line argument definition
pytorch_*.py (6 files)	Implements the timing logic to start measurement after GPU data copy when --no_copy is enabled
test_model_base.py	Updates test documentation to include the new --no_copy option

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}