Bump Mellanox Tools (#3597)

mosaicml · Sep 3, 2024 · 5230bdc · 5230bdc
1 parent 8c4eaba
commit 5230bdc
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/docker/build_matrix.yaml b/docker/build_matrix.yaml
@@ -3,7 +3,7 @@
   BASE_IMAGE: nvidia/cuda:12.4.1-cudnn-devel-ubuntu20.04
   CUDA_VERSION: 12.4.1
   IMAGE_NAME: torch-2-4-0-cu124
-  MOFED_VERSION: latest-23.10
+  MOFED_VERSION: latest-24.07
   NVIDIA_REQUIRE_CUDA_OVERRIDE: ''
   PYTHON_VERSION: '3.11'
   PYTORCH_NIGHTLY_URL: ''
@@ -54,7 +54,7 @@
   BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04
   CUDA_VERSION: 12.1.1
   IMAGE_NAME: torch-2-3-1-cu121
-  MOFED_VERSION: latest-23.10
+  MOFED_VERSION: latest-24.07
   NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471
     brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471
     brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471
@@ -125,7 +125,7 @@
   BASE_IMAGE: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04
   CUDA_VERSION: 12.1.1
   IMAGE_NAME: torch-2-2-2-cu121
-  MOFED_VERSION: latest-23.10
+  MOFED_VERSION: latest-24.07
   NVIDIA_REQUIRE_CUDA_OVERRIDE: cuda>=12.1 brand=tesla,driver>=450,driver<451 brand=tesla,driver>=470,driver<471
     brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471
     brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471

diff --git a/docker/generate_build_matrix.py b/docker/generate_build_matrix.py
@@ -231,7 +231,7 @@ def _main():
         if not cuda_version or interconnect == 'EFA':
             entry['MOFED_VERSION'] = ''
         else:
-            entry['MOFED_VERSION'] = 'latest-23.10'
+            entry['MOFED_VERSION'] = 'latest-24.07'
 
         # Skip EFA drivers if not using EFA
         if interconnect != 'EFA':