[None][fix] Fixed regex in test_trtllm_bench_backend_comparison #7316
Conversation
Signed-off-by: Eran Geva <[email protected]>
📝 WalkthroughWalkthroughUpdated a unit-test helper in Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Suggested reviewers
Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. ✨ Finishing Touches
🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
|
/bot run |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py (2)
76-92: Unit mismatch: captured value is now MB but downstream expects bytes. Convert and support both log formats.After switching the regex to the “(MB)” label, current_cache_size is parsed in MB, but:
- validate_kv_cache_metrics_dynamic compares it against 16,777,216 (bytes).
- new_cache_size adds bytes (from free_mem_post_mb10241024) to this MB value.
This will break correctness. Fix by accepting both legacy and MB formats and normalizing to bytes.Apply this diff to normalize units and remain backward-compatible:
def parse_kv_cache_metrics(log_output: str, free_mem_ratio: float = 0.8): """Parse KV cache metrics from the benchmark log output.""" metrics = {} # Simple patterns based on actual log format - patterns = { - "current_cache_size": r"Current cache size \(MB\):\s*(\d+)", - "free_mem_pre_mb": r"Free memory before forward pass \(MB\):\s*(\d+)", - "free_mem_post_mb": r"Free memory after forward pass \(MB\):\s*(\d+)", - } + patterns = { + "free_mem_pre_mb": r"Free memory before forward pass \(MB\):\s*(\d+)", + "free_mem_post_mb": r"Free memory after forward pass \(MB\):\s*(\d+)", + } + + # Extract current_cache_size with support for both legacy (bytes) and new (MB) labels. + cc_mb = re.search(r"Current cache size\s*\(MB\):\s*(\d+)", log_output, re.IGNORECASE) + cc_bytes = re.search(r"Current cache size:\s*(\d+)", log_output, re.IGNORECASE) + if cc_mb: + metrics["current_cache_size"] = int(cc_mb.group(1)) * 1024 * 1024 # normalize to bytes + print(f" ✅ Found current_cache_size: {metrics['current_cache_size']}") + elif cc_bytes: + metrics["current_cache_size"] = int(cc_bytes.group(1)) # already bytes + print(f" ✅ Found current_cache_size: {metrics['current_cache_size']}") + else: + print(" ❌ Could not find current_cache_size") # Extract metrics using simple regex patterns - for metric_name, pattern in patterns.items(): + for metric_name, pattern in patterns.items(): match = re.search(pattern, log_output, re.IGNORECASE) if match: value = int(match.group(1)) metrics[metric_name] = value print(f" ✅ Found {metric_name}: {value}") else: print(f" ❌ Could not find {metric_name}")
1-1: Add NVIDIA Copyright Header
Please prepend the standard 2025 NVIDIA header to this Python test file.• File:
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py
• Location: top of file, above the existingimport jsonSuggested diff:
+# Copyright 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved. import jsonThis matches the format used in other Python tests (e.g.
all_models/tests/test_llmapi_python_backend.py).
🧹 Nitpick comments (2)
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py (2)
72-74: Clarify units in docstring to prevent regressions.Add that current_cache_size is returned in bytes; free_mem_* are MB. Helps future maintenance.
-def parse_kv_cache_metrics(log_output: str, free_mem_ratio: float = 0.8): - """Parse KV cache metrics from the benchmark log output.""" +def parse_kv_cache_metrics(log_output: str, free_mem_ratio: float = 0.8): + """Parse KV cache metrics from the benchmark log output. + + Returns: + dict with: + - current_cache_size (bytes) + - free_mem_pre_mb (MB) + - free_mem_post_mb (MB) + - new_cache_size (bytes, computed) + """
150-165: Optional: align Python executable usage.This file mixes "python" and "python3" for subprocesses. For CI reproducibility, standardize (whichever the repo mandates). Not blocking this PR.
- "python", + "python3",
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Code must target Python 3.8+
Indent Python code with 4 spaces; do not use tabs
Preserve module namespaces when importing; import modules/packages and access members via the module (e.g., from package.subpackage import foo; foo.SomeClass())
Python file names should be snake_case
Python class names should be PascalCase
Python functions/methods and local variables should be snake_case; variables beginning with a number should be prefixed with k_ (e.g., k_99th_percentile)
Global variables should be UPPER_SNAKE_CASE prefixed with G_ (e.g., G_MY_GLOBAL); constants should be UPPER_SNAKE_CASE
Avoid shadowing variables from outer scopes; initialize all externally visible members in init
Prefer docstrings for interfaces used outside a file; comments should be reserved for in-function or file-local interfaces
Use Google-style docstrings for classes and functions; attributes and variables may be documented inline with trailing string literals
Avoid reflection when simpler, explicit code suffices (e.g., avoid dict(**locals()) patterns)
In try/except, catch the narrowest exceptions possible
For duck-typing patterns, keep the try body minimal and move logic to else to avoid masking unrelated failures
Files:
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py
**/*.{c,cc,cpp,cxx,h,hh,hpp,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend the NVIDIA copyright header (current year) to all source files (.cpp, .h, .cu, .py, etc.)
Files:
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Pre-commit Check
|
PR_Github #16744 [ run ] triggered by Bot |
|
PR_Github #16744 [ run ] completed with state |
|
/bot run |
|
PR_Github #16791 [ run ] triggered by Bot |
|
PR_Github #16791 [ run ] completed with state |
|
/bot run |
|
PR_Github #16795 [ run ] triggered by Bot |
|
PR_Github #16795 [ run ] completed with state |
|
/bot run |
|
PR_Github #16813 [ run ] triggered by Bot |
|
PR_Github #16813 [ run ] completed with state |
Signed-off-by: Eran Geva <[email protected]>
|
/bot run |
|
PR_Github #16847 [ run ] triggered by Bot |
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py (1)
1-1: Add required NVIDIA copyright header (2025).Repository guidelines require the NVIDIA copyright header on all .py files.
+# Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved. +
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py(2 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Code must target Python 3.8+
Indent with 4 spaces; do not use tabs
Preserve module namespaces in imports: import the subpackage/module, not the symbol (from package.subpackage import foo; foo.SomeClass())
Naming: files snake_case; classes PascalCase; functions/methods snake_case; local variables snake_case (k_ prefix if starting with a number); globals G_ + UPPER_SNAKE_CASE; constants UPPER_SNAKE_CASE
Avoid shadowing outer-scope variables; initialize all externally visible members in init
Prefer docstrings for interfaces used outside a file; reserve comments for function-internal or file-local interfaces
Use Google-style docstrings for classes and functions; inline docstrings for attributes/variables are allowed
Avoid reflection when straightforward code suffices (e.g., prefer explicit parameters over dict(**locals()))
Use narrow except clauses (e.g., catch FileNotFoundError instead of bare except)
For duck-typing try/except, keep try body minimal and use else for the main logic
Files:
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py
**/*.{cpp,cc,cxx,cu,h,hpp,hh,hxx,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header with current year to all source files
Files:
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py
🔇 Additional comments (1)
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py (1)
78-81: Tests correctly match the only log format used by the code—always “(MB)”—so no change is needed.Likely an incorrect or invalid review comment.
| try: | ||
| metrics["current_cache_size"] = metrics["current_cache_size"] * 1024 * 1024 | ||
| except KeyError: | ||
| print(" ❌ Could not find current_cache_size") |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Unconditional MB→bytes conversion is incorrect and duplicates “not found” logging.
Parse both formats explicitly and convert only when units are MB. Also avoid double “not found” messages.
- try:
- metrics["current_cache_size"] = metrics["current_cache_size"] * 1024 * 1024
- except KeyError:
- print(" ❌ Could not find current_cache_size")
+ # Support both "Current cache size (MB): <mb>" and "Current cache size: <bytes>"
+ m_mb = re.search(r"Current cache size\s*\(MB\):\s*([\d.]+)", log_output, re.IGNORECASE)
+ m_bytes = re.search(r"Current cache size\s*:\s*(\d+)", log_output, re.IGNORECASE)
+ if m_mb:
+ current_mb = float(m_mb.group(1))
+ metrics["current_cache_size"] = int(current_mb * 1024 * 1024)
+ print(f" ✅ Found current_cache_size (MB): {current_mb} -> {metrics['current_cache_size']} bytes")
+ elif m_bytes:
+ metrics["current_cache_size"] = int(m_bytes.group(1))
+ print(f" ✅ Found current_cache_size (bytes): {metrics['current_cache_size']}")
+ else:
+ print(" ❌ Could not find current_cache_size")🤖 Prompt for AI Agents
In tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py
around lines 92–95, the code unconditionally multiplies
metrics["current_cache_size"] by 1024*1024 and uses an except KeyError that
causes duplicate "not found" output; instead, first check presence with
metrics.get("current_cache_size"), if missing print a single "Could not find
current_cache_size" and return; if present, handle both formats: if the value is
a string ending with 'MB' (case-insensitive) parse the numeric part and multiply
by 1024*1024 to convert to bytes; if the value is a string ending with 'B' or a
plain numeric string parse it as bytes (no conversion); if it's already an
int/float treat it as bytes (no conversion); avoid raising KeyError so no
duplicate logs.
|
PR_Github #16847 [ run ] completed with state |
2 participants
Summary by CodeRabbit
Description
Test Coverage
GitHub Bot Help
/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...Provide a user friendly way for developers to interact with a Jenkins server.
Run
/bot [-h|--help]to print this help message.See details below for each supported subcommand.
run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]Launch build/test pipelines. All previously running jobs will be killed.
--reuse-test (optional)pipeline-id(OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.--disable-reuse-test(OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.--disable-fail-fast(OPTIONAL) : Disable fail fast on build/tests/infra failures.--skip-test(OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.--gpu-type "A30, H100_PCIe"(OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.--test-backend "pytorch, cpp"(OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.--add-multi-gpu-test(OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.--post-merge(OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".--detailed-log(OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.--debug(OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in thestage-listparameter to access the appropriate container environment. Note: Does NOT update GitHub check status.For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip testing for latest commit on pull request.
--comment "Reason for skipping build/test"is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.reuse-pipeline
reuse-pipelineReuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.