[None][test] Update Nemotron-3-Super-120B-A12B-NVFP4 MTP perf case with the real dataset on DGX-Spark#12982
Conversation
📝 WalkthroughWalkthroughThe PR splits the Nemotron-3-Super-120B-NVFP4 model configuration into two separate variants: one without speculative decoding and another with MTP-based speculative decoding. Both variants now include extended KV cache and SSM cache configuration settings. Test infrastructure is updated to support custom dataset generation for performance benchmarking, and test matrix entries are adjusted to reflect the new model variants. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~22 minutes 🚥 Pre-merge checks | ✅ 1 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
There was a problem hiding this comment.
Actionable comments posted: 2
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
tests/integration/defs/perf/test_perf.py (1)
1-1:⚠️ Potential issue | 🟡 MinorUpdate the copyright year.
This file is modified in this 2026 PR, but the header still ends at 2025.
As per coding guidelines,
**/*.{cpp,cc,cxx,h,hpp,py}files should "update year on modified files".🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@tests/integration/defs/perf/test_perf.py` at line 1, Update the SPDX copyright header in the file by extending the year range to include 2026: replace the current SPDX-FileCopyrightText line that ends with "2025" so it reads through "2026" (i.e., change the year range on the top-line SPDX header).
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@tests/integration/defs/perf/test_perf.py`:
- Around line 1488-1518: The current sampling only truncates prompt_ids but
still emits shorter contexts; update the loop around tokenizer.encode/decode so
that after computing prompt_ids you enforce input_len by skipping any sample
with len(prompt_ids) < input_len (or otherwise pad to input_len if you prefer),
e.g., check len(prompt_ids) and continue the sampling loop when it's shorter,
keeping the existing truncation branch intact; apply this change around the
prompt/prompt_ids/prompt_text creation and before writing the sample so
req_count only increments for samples meeting input_len.
- Around line 1590-1603: get_commands() currently calls
generate_trtllm_custom_dataset() directly (using SPEC_DEC_REAL_DATASET_MODELS)
which performs imports and I/O outside the managed llm_venv; change it so
get_commands() does NOT call generate_trtllm_custom_dataset() inline but instead
constructs the dataset file path (real_dataset_path) and appends a dataset-prep
command string to data_cmds that, when executed by
PerfServeScriptTestCmds.run_cmd(), will invoke the same generation logic inside
the managed environment; remove the immediate call to
generate_trtllm_custom_dataset() in get_commands(), ensure the command
references the same input_len/output_len and dataset_source variables, and let
run_ex()/PerfServeScriptTestCmds.run_cmd() run that command so dataset imports
and I/O occur under llm_venv just like the bench path.
---
Outside diff comments:
In `@tests/integration/defs/perf/test_perf.py`:
- Line 1: Update the SPDX copyright header in the file by extending the year
range to include 2026: replace the current SPDX-FileCopyrightText line that ends
with "2025" so it reads through "2026" (i.e., change the year range on the
top-line SPDX header).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 77591721-2b25-4a52-9211-ce51293b24e8
📒 Files selected for processing (3)
tests/integration/defs/perf/pytorch_model_config.pytests/integration/defs/perf/test_perf.pytests/integration/test_lists/qa/llm_spark_perf.yml
|
/bot run |
|
PR_Github #43023 [ run ] triggered by Bot. Commit: |
|
PR_Github #43023 [ run ] completed with state
|
|
/bot run |
|
PR_Github #43143 [ run ] triggered by Bot. Commit: |
|
PR_Github #43143 [ run ] completed with state
|
|
/bot run |
|
PR_Github #43187 [ run ] triggered by Bot. Commit: |
|
PR_Github #43187 [ run ] completed with state |
|
/bot run |
|
PR_Github #43332 [ run ] triggered by Bot. Commit: |
|
PR_Github #43332 [ run ] completed with state
|
|
/bot run |
|
PR_Github #43363 [ run ] triggered by Bot. Commit: |
|
PR_Github #43363 [ run ] completed with state
|
|
/bot run |
|
PR_Github #43436 [ run ] triggered by Bot. Commit: |
|
PR_Github #43436 [ run ] completed with state
|
Signed-off-by: Jenny Liu <JennyLiu-nv+JennyLiu@users.noreply.github.com>
Signed-off-by: Jenny Liu <JennyLiu-nv+JennyLiu@users.noreply.github.com>
…l test Signed-off-by: Jenny Liu <JennyLiu-nv+JennyLiu@users.noreply.github.com>
d37c8ac to
2997d5f
Compare
|
/bot run |
|
PR_Github #43615 [ run ] triggered by Bot. Commit: |
|
PR_Github #43615 [ run ] completed with state
|
|
/bot run |
|
PR_Github #43660 [ run ] triggered by Bot. Commit: |
|
PR_Github #43660 [ run ] completed with state
|
|
/bot run |
|
PR_Github #43749 [ run ] triggered by Bot. Commit: |
|
PR_Github #43749 [ run ] completed with state
|
|
/bot run |
|
PR_Github #44274 [ run ] triggered by Bot. Commit: |
|
PR_Github #44274 [ run ] completed with state
|
|
/bot run |
|
PR_Github #44301 [ run ] triggered by Bot. Commit: |
|
PR_Github #44301 [ run ] completed with state
|
|
/bot run |
|
PR_Github #44418 [ run ] triggered by Bot. Commit: |
|
PR_Github #44418 [ run ] completed with state
|
|
/bot run |
|
PR_Github #44631 [ run ] triggered by Bot. Commit: |
|
PR_Github #44631 [ run ] completed with state |
Summary by CodeRabbit
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
To see a list of available CI bot commands, please comment
/bot help.