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

Add pre-merge Triton backend tests (#4842)

Browse Source 
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
This commit is contained in:
Iman Tabrizian 2025-06-03 00:47:58 -04:00 committed by GitHub
parent fa93eeee84
commit 141467d4b6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 17 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
jenkins/L0_Test.groovy
View File

@ -1528,6 +1528,7 @@ def launchTestJobs(pipeline, testFilter, dockerNode=null)
"A10-TensorRT-4": ["a10", "l0_a10", 4, 6],
"A10-TensorRT-5": ["a10", "l0_a10", 5, 6],
"A10-TensorRT-6": ["a10", "l0_a10", 6, 6],
"A30-Triton-1": ["a30", "l0_a30", 1, 1],
"A30-PyTorch-1": ["a30", "l0_a30", 1, 2],
"A30-PyTorch-2": ["a30", "l0_a30", 2, 2],
"A30-CPP-1": ["a30", "l0_a30", 1, 2],

16
tests/integration/test_lists/test-db/l0_a30.yml
View File

@ -50,6 +50,22 @@ l0_a30:
- cpp/test_e2e.py::test_model[-gpt-80]
- cpp/test_e2e.py::test_model[-gpt_executor-80]
- cpp/test_e2e.py::test_model[-gpt_tests-80]
- condition:
ranges:
system_gpu_count:
gte: 1
lte: 1
wildcards:
gpu:
- '*a30*'
linux_distribution_name: ubuntu*
terms:
stage: pre_merge
backend: triton
tests:
- triton_server/test_triton.py::test_opt[opt]
- triton_server/test_triton_llm.py::test_llmapi_backend[1-0-disableDecoupleMode-tensorrt_llm]
- triton_server/test_triton_llm.py::test_llmapi_backend[1-0-enableDecoupleMode-tensorrt_llm]
- condition:
ranges:
system_gpu_count: