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

[TRTLLM-8930][infra] Force Blossom perf test stages to use 'tensorrt/test_type: perf' in the K8S template (#8752)

Browse Source 
Signed-off-by: ZhanruiSunCh <184402041+ZhanruiSunCh@users.noreply.github.com>
Signed-off-by: Zhanrui Sun <184402041+ZhanruiSunCh@users.noreply.github.com>
This commit is contained in:
Zhanrui Sun 2025-10-30 21:30:10 +08:00 committed by GitHub
parent f9c7786dc8
commit 547d799111
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
jenkins/L0_Test.groovy
View File

@ -1296,14 +1296,14 @@ def createKubernetesPodConfig(image, type, arch = "amd64", gpuCount = 1, perfMod
kubernetes.io/os: linux
nvidia.com/gpu_type: ${gpuType}"""
} else if (perfMode && !hasMultipleGPUs) {
// Not using the "perf" node currently due to hardware resource constraint.
// Use single GPU machine with "tensorrt/test_type: perf" for stable perf testing.
// H100 / A100 single GPU machine has this unique label in TensorRT Blossom pool.
selectors = """
kubernetes.io/arch: ${arch}
kubernetes.io/os: linux
nvidia.com/gpu_type: ${gpuType}
nvidia.com/driver_version: '${driverVersion}'"""
nvidia.com/driver_version: '${driverVersion}'
tensorrt/test_type: perf"""
}
else
{