diff --git a/pyproject.toml b/pyproject.toml
index e03c8244..44d1d394 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -11,6 +11,7 @@ dependencies = [
     "click>=8.1.0",
     "rich>=13.7.0",
     "pydantic>=2.10.6",
+    "pyyaml>=6.0.2",
 ]
 
 [dependency-groups]
diff --git a/uv.lock b/uv.lock
index 523778ec..eae4c1b4 100644
--- a/uv.lock
+++ b/uv.lock
@@ -2068,7 +2068,7 @@ name = "nvidia-cudnn-cu12"
 version = "9.1.0.70"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9f/fd/713452cd72343f682b1c7b9321e23829f00b842ceaedcda96e742ea0b0b3/nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl", hash = "sha256:165764f44ef8c61fcdfdfdbe769d687e06374059fbb388b6c89ecb0e28793a6f", size = 664752741 },
@@ -2079,7 +2079,7 @@ name = "nvidia-cufft-cu12"
 version = "11.2.1.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink-cu12" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/27/94/3266821f65b92b3138631e9c8e7fe1fb513804ac934485a8d05776e1dd43/nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl", hash = "sha256:f083fc24912aa410be21fa16d157fed2055dab1cc4b6934a0e03cba69eb242b9", size = 211459117 },
@@ -2098,9 +2098,9 @@ name = "nvidia-cusolver-cu12"
 version = "11.6.1.9"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12" },
-    { name = "nvidia-cusparse-cu12" },
-    { name = "nvidia-nvjitlink-cu12" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/3a/e1/5b9089a4b2a4790dfdea8b3a006052cfecff58139d5a4e34cb1a51df8d6f/nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl", hash = "sha256:19e33fa442bcfd085b3086c4ebf7e8debc07cfe01e11513cc6d332fd918ac260", size = 127936057 },
@@ -2111,7 +2111,7 @@ name = "nvidia-cusparse-cu12"
 version = "12.3.1.170"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink-cu12" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/db/f7/97a9ea26ed4bbbfc2d470994b8b4f338ef663be97b8f677519ac195e113d/nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl", hash = "sha256:ea4f11a2904e2a8dc4b1833cc1b5181cde564edd0d5cd33e3c168eff2d1863f1", size = 207454763 },
@@ -3973,7 +3973,7 @@ name = "triton"
 version = "3.1.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "filelock" },
+    { name = "filelock", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/98/29/69aa56dc0b2eb2602b553881e34243475ea2afd9699be042316842788ff5/triton-3.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b0dd10a925263abbe9fa37dcde67a5e9b2383fc269fdf59f5657cac38c5d1d8", size = 209460013 },
@@ -4078,6 +4078,7 @@ source = { editable = "." }
 dependencies = [
     { name = "click" },
     { name = "pydantic" },
+    { name = "pyyaml" },
     { name = "requests" },
     { name = "rich" },
 ]
@@ -4128,6 +4129,7 @@ requires-dist = [
     { name = "click", specifier = ">=8.1.0" },
     { name = "cupy-cuda12x", marker = "extra == 'dev'", specifier = "==12.1.0" },
     { name = "pydantic", specifier = ">=2.10.6" },
+    { name = "pyyaml", specifier = ">=6.0.2" },
     { name = "ray", marker = "extra == 'dev'", specifier = ">=2.40.0" },
     { name = "requests", specifier = ">=2.31.0" },
     { name = "rich", specifier = ">=13.7.0" },
@@ -4386,8 +4388,8 @@ name = "xformers"
 version = "0.0.28.post3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "numpy" },
-    { name = "torch" },
+    { name = "numpy", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "torch", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/00/d8/7301b2044e29b384b6ec009ed37002f4df48906a2a772654e8386fa3b730/xformers-0.0.28.post3.tar.gz", hash = "sha256:c7a2392c874dfd8f38b73e14492baf048a4f50f77ddf522bfcf6ebf5ee84d567", size = 7758532 }
 wheels = [