Add NVIDIA stress loader selection and DCGM 4 support

This commit is contained in:
Mikhail Chusavitin
2026-03-31 11:15:15 +03:00
parent 20f834aa96
commit 6dee8f3509
31 changed files with 789 additions and 111 deletions

View File

@@ -1,2 +1,8 @@
# NVIDIA DCGM (Data Center GPU Manager) — dcgmi diag for acceptance testing
datacenter-gpu-manager=1:%%DCGM_VERSION%%
# NVIDIA DCGM (Data Center GPU Manager) — dcgmi diag for acceptance testing.
# DCGM 4 is packaged per CUDA major. The image ships NVIDIA driver 590 with CUDA 13 userspace,
# so install the CUDA 13 build plus proprietary diagnostic components explicitly.
datacenter-gpu-manager-4-cuda13=1:%%DCGM_VERSION%%
datacenter-gpu-manager-4-proprietary=1:%%DCGM_VERSION%%
datacenter-gpu-manager-4-proprietary-cuda13=1:%%DCGM_VERSION%%
ocl-icd-libopencl1
clinfo