Add manywheel special build for including pypi package (#1142)

* Add manywheel special build

Testing

Builder change

Testing

Adding manywheel cuda workflow

Simplify

Fix expr

* address comments

* checking for general setting

Author: atalman

manywheel/build_cuda.sh

@@ -232,42 +232,49 @@ DEPS_SONAME=(
     "libgomp.so.1"
 )
 elif [[ $CUDA_VERSION == "11.7" ]]; then
-export USE_STATIC_CUDNN=0
-DEPS_LIST=(
-    "/usr/local/cuda/lib64/libcudart.so.11.0"
-    "/usr/local/cuda/lib64/libnvToolsExt.so.1"
-    "/usr/local/cuda/lib64/libnvrtc.so.11.2"    # this is not a mistake for 11.7, it links to 11.7.50
-    "/usr/local/cuda/lib64/libnvrtc-builtins.so.11.7"
-    "/usr/local/cuda/lib64/libcudnn_adv_infer.so.8"
-    "/usr/local/cuda/lib64/libcudnn_adv_train.so.8"
-    "/usr/local/cuda/lib64/libcudnn_cnn_infer.so.8"
-    "/usr/local/cuda/lib64/libcudnn_cnn_train.so.8"
-    "/usr/local/cuda/lib64/libcudnn_ops_infer.so.8"
-    "/usr/local/cuda/lib64/libcudnn_ops_train.so.8"
-    "/usr/local/cuda/lib64/libcudnn.so.8"
-    "/usr/local/cuda/lib64/libcublas.so.11"
-    "/usr/local/cuda/lib64/libcublasLt.so.11"
-    "$LIBGOMP_PATH"
-)
-DEPS_SONAME=(
-    "libcudart.so.11.0"
-    "libnvToolsExt.so.1"
-    "libnvrtc.so.11.2"
-    "libnvrtc-builtins.so.11.7"
-    "libcudnn_adv_infer.so.8"
-    "libcudnn_adv_train.so.8"
-    "libcudnn_cnn_infer.so.8"
-    "libcudnn_cnn_train.so.8"
-    "libcudnn_ops_infer.so.8"
-    "libcudnn_ops_train.so.8"
-    "libcudnn.so.8"
-    "libcublas.so.11"
-    "libcublasLt.so.11"
-    "libgomp.so.1"
-)
+    export USE_STATIC_CUDNN=0
+    # Try parallelizing nvcc as well
+    export TORCH_NVCC_FLAGS="-Xfatbin -compress-all --threads 2"
+    DEPS_LIST=(
+        "/usr/local/cuda/lib64/libcudart.so.11.0"
+        "/usr/local/cuda/lib64/libnvToolsExt.so.1"
+        "/usr/local/cuda/lib64/libnvrtc.so.11.2"    # this is not a mistake for 11.7, it links to 11.7.50
+        "/usr/local/cuda/lib64/libnvrtc-builtins.so.11.7"
+        "$LIBGOMP_PATH"
+    )
+    DEPS_SONAME=(
+        "libcudart.so.11.0"
+        "libnvToolsExt.so.1"
+        "libnvrtc.so.11.2"
+        "libnvrtc-builtins.so.11.7"
+        "libgomp.so.1"
+    )
 
-# Try parallelizing nvcc as well
-export TORCH_NVCC_FLAGS="-Xfatbin -compress-all --threads 2"
+    if [[ -z "$PYTORCH_EXTRA_INSTALL_REQUIREMENTS" ]]; then
+        echo "Bundling with cudnn and cublas."
+        DEPS_LIST+=(
+            "/usr/local/cuda/lib64/libcudnn_adv_infer.so.8"
+            "/usr/local/cuda/lib64/libcudnn_adv_train.so.8"
+            "/usr/local/cuda/lib64/libcudnn_cnn_infer.so.8"
+            "/usr/local/cuda/lib64/libcudnn_cnn_train.so.8"
+            "/usr/local/cuda/lib64/libcudnn_ops_infer.so.8"
+            "/usr/local/cuda/lib64/libcudnn_ops_train.so.8"
+            "/usr/local/cuda/lib64/libcudnn.so.8"
+            "/usr/local/cuda/lib64/libcublas.so.11"
+            "/usr/local/cuda/lib64/libcublasLt.so.11"
+        )
+        DEPS_SONAME+=(
+            "libcudnn_adv_infer.so.8"
+            "libcudnn_adv_train.so.8"
+            "libcudnn_cnn_infer.so.8"
+            "libcudnn_cnn_train.so.8"
+            "libcudnn_ops_infer.so.8"
+            "libcudnn_ops_train.so.8"
+            "libcudnn.so.8"
+            "libcublas.so.11"
+            "libcublasLt.so.11"
+        )
+    fi
 else
     echo "Unknown cuda version $CUDA_VERSION"
     exit 1