diff --git a/pyproject.toml b/pyproject.toml
index 70eb0d5..434b6eb 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -63,7 +63,9 @@ cuda = [
     "mpi4py==4.1.1",
 ]
 rocm = [
-    "torch==2.12.0+rocm7.2",
+    "torch==2.12.0+rocm7.1",
+    "torchaudio==2.11.0+rocm7.1",
+    "torchvision==0.27.0+rocm7.1",
     "mpi4py==4.1.1",
 ]
 rocmwci = [
diff --git a/scripts/install-tuolumne-torchpypi.sh b/scripts/install-tuolumne-torchpypi.sh
index 91876c4..0b7c597 100644
--- a/scripts/install-tuolumne-torchpypi.sh
+++ b/scripts/install-tuolumne-torchpypi.sh
@@ -1,5 +1,5 @@
-ml load python/3.11.5 && python3 -m venv .venvs/scaffoldvenv-tuo-pypi && source .venvs/scaffoldvenv-tuo-pypi/bin/activate && pip install --upgrade pip
-ml cce/21.0.1 cray-mpich/9.1.0 rocm/7.2.1 rccl/fast-env-slows-mpi
-pip install -e .[rocm] --find-links https://download.pytorch.org/whl/torch/ --find-links https://download.pytorch.org/whl/triton-rocm/ 2>&1 | tee install.log
+ml load python/3.13.2 && python3 -m venv .venvs/scaffoldvenv-tuo-pypi && source .venvs/scaffoldvenv-tuo-pypi/bin/activate && pip install --upgrade pip
+ml cce/21.0.1 cray-mpich/9.1.0 rocm/7.1.1 rccl/fast-env-slows-mpi
+pip install -e .[rocm] --find-links https://download.pytorch.org/whl/torch/ --find-links https://download.pytorch.org/whl/torchaudio/ --find-links https://download.pytorch.org/whl/torchvision/ --find-links https://download.pytorch.org/whl/triton-rocm/ 2>&1 | tee install.log
 # libmpi.so.12 does not exist => ls /opt/cray/pe/lib64/ | grep libmpi
-patchelf --replace-needed libmpi.so.12 libmpi_gnu.so.12 .venvs/scaffoldvenv-tuo-pypi/lib/python3.11/site-packages/mpi4py/MPI.mpich.cpython-311-x86_64-linux-gnu.so
+patchelf --replace-needed libmpi.so.12 libmpi_gnu.so.12 .venvs/scaffoldvenv-tuo-pypi/lib/python3.13/site-packages/mpi4py/MPI.mpich.cpython-313-x86_64-linux-gnu.so
diff --git a/scripts/scaffold-tuolumne-torchpypi.job b/scripts/scaffold-tuolumne-torchpypi.job
index c78af96..cc3b061 100644
--- a/scripts/scaffold-tuolumne-torchpypi.job
+++ b/scripts/scaffold-tuolumne-torchpypi.job
@@ -7,20 +7,20 @@
 # flux: -qpdebug
 # flux: -B flask
 
-ml cce/21.0.1 cray-mpich/9.1.0 rocm/7.2.1 rccl/fast-env-slows-mpi
+ml cce/21.0.1 cray-mpich/9.1.0 rocm/7.1.1 rccl/fast-env-slows-mpi
 
 . .venvs/scaffoldvenv-tuo-pypi/bin/activate
 
-export NCCL_NET_PLUGIN=/collab/usr/global/tools/rccl/toss_4_x86_64_ib_cray/rocm-7.2.0/install/lib/librccl-net.so
+export NCCL_NET_PLUGIN=/collab/usr/global/tools/rccl/toss_4_x86_64_ib_cray/rocm-7.1.1/install/lib/librccl-net.so
 
 # Disable direct convolution benchmarking (should speedup warmup by a significant amount, does the below three options together)
-# export MIOPEN_DEBUG_CONV_DIRECT=0
+export MIOPEN_DEBUG_CONV_DIRECT=0
 # Disable direct naive convolution benchmarking (naive_conv_ab_nonpacked_fwd_ndhwc_half_double_half.kd)
-export MIOPEN_DEBUG_CONV_DIRECT_NAIVE_CONV_FWD=0
+# export MIOPEN_DEBUG_CONV_DIRECT_NAIVE_CONV_FWD=0
 # Disable naive_conv_ab_nonpacked_bwd_ndhwc_half_double_half.kd
-export MIOPEN_DEBUG_CONV_DIRECT_NAIVE_CONV_BWD=0
+# export MIOPEN_DEBUG_CONV_DIRECT_NAIVE_CONV_BWD=0
 # Disable naive_conv_ab_nonpacked_wrw_ndhwc_half_double_half.kd
-export MIOPEN_DEBUG_CONV_DIRECT_NAIVE_CONV_WRW=0
+# export MIOPEN_DEBUG_CONV_DIRECT_NAIVE_CONV_WRW=0
 
 CONFIG_PATH="$(pwd)/ScaFFold/configs/benchmark_default.yml"
 FRACT_BASE_DIR="${FRACT_BASE_DIR:-$(pwd)/ScaFFold/fractals}"