kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

test(perf): Add remaining Phi-4-mini-instruct perf tests (#4443)

Browse Source 
add remaining 2 phi cpp perf tests

Signed-off-by: Venky <23023424+venkywonka@users.noreply.github.com>
Co-authored-by: Larry <197874197+LarryXFly@users.noreply.github.com>
This commit is contained in:
Venky 2025-05-20 18:26:12 -07:00 committed by GitHub
parent 19c6e68bec
commit 9a8c3ece22
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/integration/test_lists/qa/trt_llm_release_perf_test.yml
View File

@ -82,6 +82,9 @@ trt_llm_release_perf_test:
- perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:5000,500-quant:fp8-con:250]
- perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:500,2000-con:250]
- perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:500,2000-quant:fp8-con:250]
# reduced 'reqs' to fit timeout limit
- perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:500,2000-reqs:8-con:1]
- perf/test_perf.py::test_perf[phi_4_mini_instruct-bench-bfloat16-maxbs:32-input_output_len:500,2000-quant:fp8-reqs:8-con:1]
# Test list validation
- test_list_validation.py::test_list_validation