From 241bffded38fb81da533b5c4902c933270ba042a Mon Sep 17 00:00:00 2001
From: Logan Adams <114770087+loadams@users.noreply.github.com>
Date: Fri, 31 Jan 2025 15:07:12 -0800
Subject: [PATCH] Update A6000 workflows to use newer docker container - 24.09
 vs 24.03 (#6967)

- Issues with nv-sd updates, will follow up with a subsequent PR
---
 .github/workflows/nv-a6000.yml      | 6 +++---
 .github/workflows/nv-flash-attn.yml | 4 ++--
 .github/workflows/nv-human-eval.yml | 4 ++--
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/.github/workflows/nv-a6000.yml b/.github/workflows/nv-a6000.yml
index 0547431e3099..e48d9a7fffa2 100644
--- a/.github/workflows/nv-a6000.yml
+++ b/.github/workflows/nv-a6000.yml
@@ -23,7 +23,7 @@ jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, a6000]
     container:
-      image: nvcr.io/nvidia/pytorch:24.03-py3
+      image: nvcr.io/nvidia/pytorch:24.09-py3
       ports:
         - 80
       options: --gpus all --shm-size "8G"
@@ -57,8 +57,8 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2' unit/ --torch_ver="2.3" --cuda_ver="12"
-          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.3" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2' unit/ --torch_ver="2.5" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.5" --cuda_ver="12"
       - name: MII unit tests
         run: |
           BRANCH="main"
diff --git a/.github/workflows/nv-flash-attn.yml b/.github/workflows/nv-flash-attn.yml
index 310972323043..591969fbd986 100644
--- a/.github/workflows/nv-flash-attn.yml
+++ b/.github/workflows/nv-flash-attn.yml
@@ -18,7 +18,7 @@ jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, a6000]
     container:
-      image: nvcr.io/nvidia/pytorch:24.03-py3
+      image: nvcr.io/nvidia/pytorch:24.09-py3
       ports:
         - 80
       options: --gpus all --shm-size "8G"
@@ -53,7 +53,7 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          python -m pytest --color=yes --durations=0 --verbose -rF unit/sequence_parallelism/test_ulysses.py --torch_ver="2.3" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF unit/sequence_parallelism/test_ulysses.py --torch_ver="2.5" --cuda_ver="12"
       - name: Open GitHub issue if nightly CI fails
         if: ${{ failure() && (github.event_name == 'schedule') }}
         uses: JasonEtco/create-an-issue@v2
diff --git a/.github/workflows/nv-human-eval.yml b/.github/workflows/nv-human-eval.yml
index 2ecdf218b96a..3f59c42f697e 100644
--- a/.github/workflows/nv-human-eval.yml
+++ b/.github/workflows/nv-human-eval.yml
@@ -11,7 +11,7 @@ jobs:
   unit-tests:
     runs-on: [self-hosted, nvidia, a6000]
     container:
-      image: nvcr.io/nvidia/pytorch:24.03-py3
+      image: nvcr.io/nvidia/pytorch:24.09-py3
       ports:
         - 80
       options: --gpus all --shm-size "8G"
@@ -50,4 +50,4 @@ jobs:
         run: |
           unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
           cd tests
-          python -m pytest --color=yes --durations=0 --verbose -rF -m 'evaluation' -k "test_human_eval" unit/ --torch_ver="2.3" --cuda_ver="12"
+          python -m pytest --color=yes --durations=0 --verbose -rF -m 'evaluation' -k "test_human_eval" unit/ --torch_ver="2.5" --cuda_ver="12"