Uploaded using `kernel-builder`.

.gitattributes

@@ -165,3 +165,12 @@ build/torch211-cxx11-cu130-aarch64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs di
 build/torch212-cxx11-cu126-aarch64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text
 build/torch212-cxx11-cu130-aarch64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text
 build/torch212-cxx11-cu132-aarch64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text
+build/torch210-cxx11-cu126-x86_64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text
+build/torch210-cxx11-cu128-x86_64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text
+build/torch210-cxx11-cu130-x86_64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text
+build/torch211-cxx11-cu126-x86_64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text
+build/torch211-cxx11-cu128-x86_64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text
+build/torch211-cxx11-cu130-x86_64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text
+build/torch212-cxx11-cu126-x86_64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text
+build/torch212-cxx11-cu130-x86_64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text
+build/torch212-cxx11-cu132-x86_64-linux/_mra_cuda_10efe7e.abi3.so filter=lfs diff=lfs merge=lfs -text

build/torch210-cxx11-cu126-x86_64-linux/{_mra_cuda_86f75d9.abi3.so → _mra_cuda_10efe7e.abi3.so}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aafad2a759af095aac2f203e003a04b8a6f835c6841debb8b38d838fbce7e28
+oid sha256:5e54b57c1aefae767870d42cb2a9e64b66918cd74bf1919bbef453181c2c95ae
 size 2451480

build/torch210-cxx11-cu126-x86_64-linux/_ops.py

@@ -1,9 +1,9 @@
 import torch
-from . import _mra_cuda_86f75d9
-ops = torch.ops._mra_cuda_86f75d9
+from . import _mra_cuda_10efe7e
+ops = torch.ops._mra_cuda_10efe7e
 
 def add_op_namespace_prefix(op_name: str):
     """
     Prefix op by namespace.
     """
-    return f"_mra_cuda_86f75d9::{op_name}"
+    return f"_mra_cuda_10efe7e::{op_name}"

build/torch210-cxx11-cu126-x86_64-linux/metadata.json

@@ -1,6 +1,6 @@
 {
   "name": "mra",
-  "id": "_mra_cuda_86f75d9",
+  "id": "_mra_cuda_10efe7e",
   "version": 1,
   "license": "Apache-2.0",
   "python-depends": [],

build/{torch211-cxx11-cu128-x86_64-linux/_mra_cuda_86f75d9.abi3.so → torch210-cxx11-cu128-x86_64-linux/_mra_cuda_10efe7e.abi3.so}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c976bee5579f8b6d8b7081a166bcf587c3113a098e6080c9a5124172c652bc
+oid sha256:a12921f8eb17dc9c737c4e3b4f7623d5401cd4eb9e4b6d33cbf796ad6672e520
 size 2719848

build/torch210-cxx11-cu128-x86_64-linux/_ops.py

@@ -1,9 +1,9 @@
 import torch
-from . import _mra_cuda_86f75d9
-ops = torch.ops._mra_cuda_86f75d9
+from . import _mra_cuda_10efe7e
+ops = torch.ops._mra_cuda_10efe7e
 
 def add_op_namespace_prefix(op_name: str):
     """
     Prefix op by namespace.
     """
-    return f"_mra_cuda_86f75d9::{op_name}"
+    return f"_mra_cuda_10efe7e::{op_name}"

build/torch210-cxx11-cu128-x86_64-linux/metadata.json

@@ -1,6 +1,6 @@
 {
   "name": "mra",
-  "id": "_mra_cuda_86f75d9",
+  "id": "_mra_cuda_10efe7e",
   "version": 1,
   "license": "Apache-2.0",
   "python-depends": [],

build/{torch211-cxx11-cu130-x86_64-linux/_mra_cuda_86f75d9.abi3.so → torch210-cxx11-cu130-x86_64-linux/_mra_cuda_10efe7e.abi3.so}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e640ffb1150c10b48c60f5cccc969409f0ac5c93307344b7b0c429e2a3871de5
+oid sha256:8cd2210ca0390e2eb965daeb12abdd438aa2a824a180f70bf5d51460bbcae000
 size 2641648

build/torch210-cxx11-cu130-x86_64-linux/_ops.py

@@ -1,9 +1,9 @@
 import torch
-from . import _mra_cuda_86f75d9
-ops = torch.ops._mra_cuda_86f75d9
+from . import _mra_cuda_10efe7e
+ops = torch.ops._mra_cuda_10efe7e
 
 def add_op_namespace_prefix(op_name: str):
     """
     Prefix op by namespace.
     """
-    return f"_mra_cuda_86f75d9::{op_name}"
+    return f"_mra_cuda_10efe7e::{op_name}"

build/torch210-cxx11-cu130-x86_64-linux/metadata.json

@@ -1,6 +1,6 @@
 {
   "name": "mra",
-  "id": "_mra_cuda_86f75d9",
+  "id": "_mra_cuda_10efe7e",
   "version": 1,
   "license": "Apache-2.0",
   "python-depends": [],

build/torch211-cxx11-cu126-x86_64-linux/{_mra_cuda_86f75d9.abi3.so → _mra_cuda_10efe7e.abi3.so}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcf60c6e5f025c2e8d9074962eb93ac46372d0972994c4dd2218ab8348ddf9d8
+oid sha256:95d8423cb866fcdd909f1613c4b5d25143e0ca9016d31e1a2d64443a6e1d91d4
 size 2451480

build/torch211-cxx11-cu126-x86_64-linux/_ops.py

@@ -1,9 +1,9 @@
 import torch
-from . import _mra_cuda_86f75d9
-ops = torch.ops._mra_cuda_86f75d9
+from . import _mra_cuda_10efe7e
+ops = torch.ops._mra_cuda_10efe7e
 
 def add_op_namespace_prefix(op_name: str):
     """
     Prefix op by namespace.
     """
-    return f"_mra_cuda_86f75d9::{op_name}"
+    return f"_mra_cuda_10efe7e::{op_name}"

build/torch211-cxx11-cu126-x86_64-linux/metadata.json

@@ -1,6 +1,6 @@
 {
   "name": "mra",
-  "id": "_mra_cuda_86f75d9",
+  "id": "_mra_cuda_10efe7e",
   "version": 1,
   "license": "Apache-2.0",
   "python-depends": [],

build/{torch210-cxx11-cu128-x86_64-linux/_mra_cuda_86f75d9.abi3.so → torch211-cxx11-cu128-x86_64-linux/_mra_cuda_10efe7e.abi3.so}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a899fc473f4ed1b0a39c4c211015adcf9cb299cfb76b9e6a31dbf7b3fcfd58d7
+oid sha256:9f12669f16aae0189daddd00ee8a9bd9aaf502f709d2722c9529eec3dbcd4fe4
 size 2719848

build/torch211-cxx11-cu128-x86_64-linux/_ops.py

@@ -1,9 +1,9 @@
 import torch
-from . import _mra_cuda_86f75d9
-ops = torch.ops._mra_cuda_86f75d9
+from . import _mra_cuda_10efe7e
+ops = torch.ops._mra_cuda_10efe7e
 
 def add_op_namespace_prefix(op_name: str):
     """
     Prefix op by namespace.
     """
-    return f"_mra_cuda_86f75d9::{op_name}"
+    return f"_mra_cuda_10efe7e::{op_name}"

build/torch211-cxx11-cu128-x86_64-linux/metadata.json

@@ -1,6 +1,6 @@
 {
   "name": "mra",
-  "id": "_mra_cuda_86f75d9",
+  "id": "_mra_cuda_10efe7e",
   "version": 1,
   "license": "Apache-2.0",
   "python-depends": [],

build/{torch210-cxx11-cu130-x86_64-linux/_mra_cuda_86f75d9.abi3.so → torch211-cxx11-cu130-x86_64-linux/_mra_cuda_10efe7e.abi3.so}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:383257eec6a36495c0fea2f70e60b24ccfb63bea4aad48a2ccefd272ec068132
+oid sha256:5d1e1e36287a248de28cff36994820aca925879526e0484a6a3adc877c4398e6
 size 2641648

build/torch211-cxx11-cu130-x86_64-linux/_ops.py

@@ -1,9 +1,9 @@
 import torch
-from . import _mra_cuda_86f75d9
-ops = torch.ops._mra_cuda_86f75d9
+from . import _mra_cuda_10efe7e
+ops = torch.ops._mra_cuda_10efe7e
 
 def add_op_namespace_prefix(op_name: str):
     """
     Prefix op by namespace.
     """
-    return f"_mra_cuda_86f75d9::{op_name}"
+    return f"_mra_cuda_10efe7e::{op_name}"

build/torch211-cxx11-cu130-x86_64-linux/metadata.json

@@ -1,6 +1,6 @@
 {
   "name": "mra",
-  "id": "_mra_cuda_86f75d9",
+  "id": "_mra_cuda_10efe7e",
   "version": 1,
   "license": "Apache-2.0",
   "python-depends": [],

build/torch212-cxx11-cu126-x86_64-linux/__init__.py

@@ -0,0 +1,25 @@
+from ._ops import ops
+import torch
+
+def index_max(index_vals: torch.Tensor, indices: torch.Tensor, A_num_block: int, B_num_block: int):
+    return ops.index_max(index_vals, indices, A_num_block, B_num_block)
+
+def mm_to_sparse(dense_A: torch.Tensor, dense_B: torch.Tensor, indices: torch.Tensor):
+    return ops.mm_to_sparse(dense_A, dense_B, indices)
+
+def sparse_dense_mm(sparse_A: torch.Tensor, indices: torch.Tensor, dense_B: torch.Tensor, A_num_block: int):
+    return ops.sparse_dense_mm(sparse_A, indices, dense_B, A_num_block)
+
+def reduce_sum(sparse_A: torch.Tensor, indices: torch.Tensor, A_num_block: int, B_num_block: int):
+    return ops.reduce_sum(sparse_A, indices, A_num_block, B_num_block)
+
+def scatter(dense_A: torch.Tensor, indices: torch.Tensor, B_num_block: int):
+    return ops.scatter(dense_A, indices, B_num_block)
+
+__all__ = [
+    "index_max",
+    "mm_to_sparse",
+    "sparse_dense_mm",
+    "reduce_sum",
+    "scatter",
+]

build/torch212-cxx11-cu126-x86_64-linux/_mra_cuda_10efe7e.abi3.so

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc867220c038e06c40a75c2861706a4c88f8818e4be8ea058cca4bcfb7781071
+size 2446448

build/torch212-cxx11-cu126-x86_64-linux/_ops.py

@@ -0,0 +1,9 @@
+import torch
+from . import _mra_cuda_10efe7e
+ops = torch.ops._mra_cuda_10efe7e
+
+def add_op_namespace_prefix(op_name: str):
+    """
+    Prefix op by namespace.
+    """
+    return f"_mra_cuda_10efe7e::{op_name}"

build/torch212-cxx11-cu126-x86_64-linux/metadata.json

@@ -0,0 +1,20 @@
+{
+  "name": "mra",
+  "id": "_mra_cuda_10efe7e",
+  "version": 1,
+  "license": "Apache-2.0",
+  "python-depends": [],
+  "backend": {
+    "type": "cuda",
+    "archs": [
+      "7.0",
+      "7.2",
+      "7.5",
+      "8.0",
+      "8.6",
+      "8.7",
+      "8.9",
+      "9.0+PTX"
+    ]
+  }
+}

build/torch212-cxx11-cu126-x86_64-linux/mra/__init__.py

@@ -0,0 +1,26 @@
+import ctypes
+import importlib.util
+import sys
+from pathlib import Path
+from types import ModuleType
+
+
+def _import_from_path(file_path: Path) -> ModuleType:
+    # We cannot use the module name as-is, after adding it to `sys.modules`,
+    # it would also be used for other imports. So, we make a module name that
+    # depends on the path for it to be unique using the hex-encoded hash of
+    # the path.
+    path_hash = "{:x}".format(ctypes.c_size_t(hash(file_path.absolute())).value)
+    module_name = path_hash
+    spec = importlib.util.spec_from_file_location(module_name, file_path)
+    if spec is None:
+        raise ImportError(f"Cannot load spec for {module_name} from {file_path}")
+    module = importlib.util.module_from_spec(spec)
+    if module is None:
+        raise ImportError(f"Cannot load module {module_name} from spec")
+    sys.modules[module_name] = module
+    spec.loader.exec_module(module)  # type: ignore
+    return module
+
+
+globals().update(vars(_import_from_path(Path(__file__).parent.parent / "__init__.py")))

build/torch212-cxx11-cu130-x86_64-linux/__init__.py

@@ -0,0 +1,25 @@
+from ._ops import ops
+import torch
+
+def index_max(index_vals: torch.Tensor, indices: torch.Tensor, A_num_block: int, B_num_block: int):
+    return ops.index_max(index_vals, indices, A_num_block, B_num_block)
+
+def mm_to_sparse(dense_A: torch.Tensor, dense_B: torch.Tensor, indices: torch.Tensor):
+    return ops.mm_to_sparse(dense_A, dense_B, indices)
+
+def sparse_dense_mm(sparse_A: torch.Tensor, indices: torch.Tensor, dense_B: torch.Tensor, A_num_block: int):
+    return ops.sparse_dense_mm(sparse_A, indices, dense_B, A_num_block)
+
+def reduce_sum(sparse_A: torch.Tensor, indices: torch.Tensor, A_num_block: int, B_num_block: int):
+    return ops.reduce_sum(sparse_A, indices, A_num_block, B_num_block)
+
+def scatter(dense_A: torch.Tensor, indices: torch.Tensor, B_num_block: int):
+    return ops.scatter(dense_A, indices, B_num_block)
+
+__all__ = [
+    "index_max",
+    "mm_to_sparse",
+    "sparse_dense_mm",
+    "reduce_sum",
+    "scatter",
+]

build/torch212-cxx11-cu130-x86_64-linux/_mra_cuda_10efe7e.abi3.so

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93821b4672177cfcd2dd5467c92312831ee94e494208d276466f8f5f847cf3f
+size 2632472

build/torch212-cxx11-cu130-x86_64-linux/_ops.py

@@ -0,0 +1,9 @@
+import torch
+from . import _mra_cuda_10efe7e
+ops = torch.ops._mra_cuda_10efe7e
+
+def add_op_namespace_prefix(op_name: str):
+    """
+    Prefix op by namespace.
+    """
+    return f"_mra_cuda_10efe7e::{op_name}"

build/torch212-cxx11-cu130-x86_64-linux/metadata.json

@@ -0,0 +1,21 @@
+{
+  "name": "mra",
+  "id": "_mra_cuda_10efe7e",
+  "version": 1,
+  "license": "Apache-2.0",
+  "python-depends": [],
+  "backend": {
+    "type": "cuda",
+    "archs": [
+      "10.0",
+      "11.0",
+      "12.0+PTX",
+      "7.5",
+      "8.0",
+      "8.6",
+      "8.7",
+      "8.9",
+      "9.0"
+    ]
+  }
+}

build/torch212-cxx11-cu130-x86_64-linux/mra/__init__.py

@@ -0,0 +1,26 @@
+import ctypes
+import importlib.util
+import sys
+from pathlib import Path
+from types import ModuleType
+
+
+def _import_from_path(file_path: Path) -> ModuleType:
+    # We cannot use the module name as-is, after adding it to `sys.modules`,
+    # it would also be used for other imports. So, we make a module name that
+    # depends on the path for it to be unique using the hex-encoded hash of
+    # the path.
+    path_hash = "{:x}".format(ctypes.c_size_t(hash(file_path.absolute())).value)
+    module_name = path_hash
+    spec = importlib.util.spec_from_file_location(module_name, file_path)
+    if spec is None:
+        raise ImportError(f"Cannot load spec for {module_name} from {file_path}")
+    module = importlib.util.module_from_spec(spec)
+    if module is None:
+        raise ImportError(f"Cannot load module {module_name} from spec")
+    sys.modules[module_name] = module
+    spec.loader.exec_module(module)  # type: ignore
+    return module
+
+
+globals().update(vars(_import_from_path(Path(__file__).parent.parent / "__init__.py")))

build/torch212-cxx11-cu132-x86_64-linux/__init__.py

@@ -0,0 +1,25 @@
+from ._ops import ops
+import torch
+
+def index_max(index_vals: torch.Tensor, indices: torch.Tensor, A_num_block: int, B_num_block: int):
+    return ops.index_max(index_vals, indices, A_num_block, B_num_block)
+
+def mm_to_sparse(dense_A: torch.Tensor, dense_B: torch.Tensor, indices: torch.Tensor):
+    return ops.mm_to_sparse(dense_A, dense_B, indices)
+
+def sparse_dense_mm(sparse_A: torch.Tensor, indices: torch.Tensor, dense_B: torch.Tensor, A_num_block: int):
+    return ops.sparse_dense_mm(sparse_A, indices, dense_B, A_num_block)
+
+def reduce_sum(sparse_A: torch.Tensor, indices: torch.Tensor, A_num_block: int, B_num_block: int):
+    return ops.reduce_sum(sparse_A, indices, A_num_block, B_num_block)
+
+def scatter(dense_A: torch.Tensor, indices: torch.Tensor, B_num_block: int):
+    return ops.scatter(dense_A, indices, B_num_block)
+
+__all__ = [
+    "index_max",
+    "mm_to_sparse",
+    "sparse_dense_mm",
+    "reduce_sum",
+    "scatter",
+]

build/torch212-cxx11-cu132-x86_64-linux/_mra_cuda_10efe7e.abi3.so

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3bf0488c644df07c7cf65068bd4ab6f5e83798201665f3a82656dc0014363b
+size 2700264

build/torch212-cxx11-cu132-x86_64-linux/_ops.py

@@ -0,0 +1,9 @@
+import torch
+from . import _mra_cuda_10efe7e
+ops = torch.ops._mra_cuda_10efe7e
+
+def add_op_namespace_prefix(op_name: str):
+    """
+    Prefix op by namespace.
+    """
+    return f"_mra_cuda_10efe7e::{op_name}"

build/torch212-cxx11-cu132-x86_64-linux/metadata.json

@@ -0,0 +1,21 @@
+{
+  "name": "mra",
+  "id": "_mra_cuda_10efe7e",
+  "version": 1,
+  "license": "Apache-2.0",
+  "python-depends": [],
+  "backend": {
+    "type": "cuda",
+    "archs": [
+      "10.0",
+      "11.0",
+      "12.0+PTX",
+      "7.5",
+      "8.0",
+      "8.6",
+      "8.7",
+      "8.9",
+      "9.0"
+    ]
+  }
+}

build/torch212-cxx11-cu132-x86_64-linux/mra/__init__.py

@@ -0,0 +1,26 @@
+import ctypes
+import importlib.util
+import sys
+from pathlib import Path
+from types import ModuleType
+
+
+def _import_from_path(file_path: Path) -> ModuleType:
+    # We cannot use the module name as-is, after adding it to `sys.modules`,
+    # it would also be used for other imports. So, we make a module name that
+    # depends on the path for it to be unique using the hex-encoded hash of
+    # the path.
+    path_hash = "{:x}".format(ctypes.c_size_t(hash(file_path.absolute())).value)
+    module_name = path_hash
+    spec = importlib.util.spec_from_file_location(module_name, file_path)
+    if spec is None:
+        raise ImportError(f"Cannot load spec for {module_name} from {file_path}")
+    module = importlib.util.module_from_spec(spec)
+    if module is None:
+        raise ImportError(f"Cannot load module {module_name} from spec")
+    sys.modules[module_name] = module
+    spec.loader.exec_module(module)  # type: ignore
+    return module
+
+
+globals().update(vars(_import_from_path(Path(__file__).parent.parent / "__init__.py")))