test(perf): Pt.2 Add Llama-3_3-Nemotron-Super-49B-v1 integration-perf-tests (cpp)
#4499
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
venkywonka
changed the title
Llama-3_3-Nemotron-Super-49B-v1 integration-perf-tests (cpp)Llama-3_3-Nemotron-Super-49B-v1 integration-perf-tests (cpp)
Signed-off-by: Venky <[email protected]>
venkywonka
force-pushed
the
user/venky/ll-nemo-super-cpp-low-con-perf-tests
branch
from
9e4e51a to
de538af
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #5898 [ run ] triggered by Bot |
venkywonka
requested review from
Copilot,
tijyojwad,
schetlur-nv,
LarryXFly and
ruodil
There was a problem hiding this comment.
Pull Request Overview
This PR enables the integration performance tests for the Llama-3.3-Nemotron-Super-49B-v1 model by adding new test configurations with adjusted parameters, reducing the number of total requests to meet the time budget.
- Enabled four new performance test cases with increased max batch sizes (64) and a reduced request count (4).
- Removed the previously commented-out timeout test cases.
Comments suppressed due to low confidence (1)
tests/integration/test_lists/qa/trt_llm_release_perf_test.yml:290
- Verify that the new 'reqs:4' setting provides adequate coverage for the intended low-concurrency performance scenarios and aligns with the overall test plan.
- perf/test_perf.py::test_perf[llama_v3.3_nemotron_super_49b-bench-bfloat16-maxbs:64-input_output_len:500,2000-reqs:4-con:1-gpus:4]
tijyojwad
approved these changes
May 20, 2025
|
PR_Github #5898 [ run ] completed with state |
LarryXFly
approved these changes
May 21, 2025
venkywonka
added a commit
to venkywonka/TensorRT-LLM
that referenced
this pull request
May 22, 2025
…rf-tests (cpp) (NVIDIA#4499) add low concurrency perf tests Signed-off-by: Venky <[email protected]>
chzblych
pushed a commit
that referenced
this pull request
May 28, 2025
…tegration-perf-tests (cpp) (#4499) (#4588) Signed-off-by: Venky <[email protected]>
darraghdog
pushed a commit
to darraghdog/TensorRT-LLM
that referenced
this pull request
Jun 3, 2025
…rf-tests (cpp) (NVIDIA#4499) add low concurrency perf tests Signed-off-by: Venky <[email protected]> Signed-off-by: darraghdog <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR adds the remaining
llama_v3.3_nemotron_super_49btests that previous timed-out on high-request settings.These tests add four new coverage points in the low-concurrency setting. (2 ctx/gen shapes × BF16/FP8)
This time, the total requests was reduced from 512->4 to fit the time budget.
Test-plan overview
Shmoo-ed parameters
input=5 000, output=500input=500, output=2 000Throughput & latency summary
(tok/s)
(tok/s)
(ms)
(ms)
Latency percentiles (ms)