Add torch211-cxx11-cu130-aarch64-linux aarch64 artifact

Browse files

Files changed (4) hide show

build/torch211-cxx11-cu130-aarch64-linux/__init__.py +32 -0
build/torch211-cxx11-cu130-aarch64-linux/_adaptive_layernorm_producers_cuda_8a66d8b.abi3.so +3 -0
build/torch211-cxx11-cu130-aarch64-linux/_ops.py +3 -3
build/torch211-cxx11-cu130-aarch64-linux/metadata.json +5 -10

build/torch211-cxx11-cu130-aarch64-linux/__init__.py CHANGED Viewed

@@ -198,6 +198,22 @@ def _layer_norm_no_affine_quant_fp8_static_bf16_fake(
     return None
 def ada_layer_norm_quant_fp8_bf16(
     x: torch.Tensor,
     scale: torch.Tensor,
@@ -353,6 +369,21 @@ def layer_norm_no_affine_quant_fp8_static_bf16(
     return out
 @torch.library.register_fake(add_op_namespace_prefix("adaln_modulation6_bf16"))
 def _adaln_modulation6_bf16_fake(
     adaln_params: torch.Tensor,
@@ -418,6 +449,7 @@ __all__ = [
     "ada_layer_norm_quant_nvfp4_swizzled_bf16",
     "ada_layer_norm_quant_nvfp4_swizzled_modfp8_bf16",
     "layer_norm_no_affine_quant_fp8_static_bf16",
     "adaln_modulation6_bf16",
     "swizzled_sf_size",
 ]

     return None
+@torch.library.register_fake(add_op_namespace_prefix("layer_norm_no_affine_quant_nvfp4_swizzled_bf16"))
+def _layer_norm_no_affine_quant_nvfp4_swizzled_bf16_fake(
+    x: torch.Tensor,
+    eps: float,
+    packed: torch.Tensor,
+    sf_swizzled: torch.Tensor,
+) -> None:
+    _check_x(x)
+    rows, dim = x.shape
+    if packed.shape != (rows, dim // 2):
+        raise RuntimeError("packed must have shape (rows, dim // 2)")
+    if sf_swizzled.numel() < swizzled_sf_size(rows, dim):
+        raise RuntimeError("sf_swizzled is too small")
+    return None
 def ada_layer_norm_quant_fp8_bf16(
     x: torch.Tensor,
     scale: torch.Tensor,
     return out
+def layer_norm_no_affine_quant_nvfp4_swizzled_bf16(
+    x: torch.Tensor,
+    eps: float = 1e-5,
+    packed: torch.Tensor | None = None,
+    sf_swizzled: torch.Tensor | None = None,
+) -> tuple[torch.Tensor, torch.Tensor]:
+    """SM110 no-affine LayerNorm producing NVFP4 and CUTLASS SFA."""
+    if packed is None or sf_swizzled is None:
+        packed, sf_swizzled = _alloc_nvfp4(x)
+    ops.layer_norm_no_affine_quant_nvfp4_swizzled_bf16(
+        x, float(eps), packed, sf_swizzled
+    )
+    return packed, sf_swizzled
 @torch.library.register_fake(add_op_namespace_prefix("adaln_modulation6_bf16"))
 def _adaln_modulation6_bf16_fake(
     adaln_params: torch.Tensor,
     "ada_layer_norm_quant_nvfp4_swizzled_bf16",
     "ada_layer_norm_quant_nvfp4_swizzled_modfp8_bf16",
     "layer_norm_no_affine_quant_fp8_static_bf16",
+    "layer_norm_no_affine_quant_nvfp4_swizzled_bf16",
     "adaln_modulation6_bf16",
     "swizzled_sf_size",
 ]

build/torch211-cxx11-cu130-aarch64-linux/_adaptive_layernorm_producers_cuda_8a66d8b.abi3.so ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a2db2e007dbc80da262c206891058c7db8c1c7f249b92ad6185c1ce11b814f
+size 535776

build/torch211-cxx11-cu130-aarch64-linux/_ops.py CHANGED Viewed

@@ -1,6 +1,6 @@
 import torch
-from . import _adaptive_layernorm_producers_cuda_7781728
-ops = torch.ops._adaptive_layernorm_producers_cuda_7781728
 def add_op_namespace_prefix(op_name: str):
-    return f"_adaptive_layernorm_producers_cuda_7781728::{op_name}"

 import torch
+from . import _adaptive_layernorm_producers_cuda_8a66d8b
+ops = torch.ops._adaptive_layernorm_producers_cuda_8a66d8b
 def add_op_namespace_prefix(op_name: str):
+    return f"_adaptive_layernorm_producers_cuda_8a66d8b::{op_name}"

build/torch211-cxx11-cu130-aarch64-linux/metadata.json CHANGED Viewed

@@ -1,33 +1,28 @@
 {
   "name": "adaptive-layernorm-producers",
-  "id": "_adaptive_layernorm_producers_cuda_7781728",
   "version": 1,
   "license": "Apache-2.0",
   "python-depends": [],
   "backend": {
     "type": "cuda",
     "archs": [
-      "8.7",
       "11.0a"
     ]
   },
   "digest": {
     "algorithm": "sha256",
     "files": {
-      "__init__.py": "Y0RRm5MDP9m0wKQRpuGRFg0YewrbqdZnVIBItbh7DAc=",
-      "_adaptive_layernorm_producers_cuda_7781728.abi3.so": "K1VCrkSDMuvU0fLKLwAw+IIABh+NLmTrhYHDFOfXMiw=",
-      "_ops.py": "kG1EL+EuLDtXPuUtyj/ygYLPUZg6eszWjMCBtbLC0pw=",
       "adaptive_layernorm_producers/__init__.py": "v6p5XMfQzddhi1fLSAw4HX9CyS0rQsidvu9VsT01xi4="
     }
   },
   "provenance": {
     "kernel": {
-      "sha": "9b532b42ad71d0ef6bc79d1372e96910087faad4",
       "dirty": false
-    },
-    "validation": {
-      "torch": "2.11.0+cu130",
-      "cuda": "13.0"
     }
   }
 }

 {
   "name": "adaptive-layernorm-producers",
+  "id": "_adaptive_layernorm_producers_cuda_8a66d8b",
   "version": 1,
   "license": "Apache-2.0",
   "python-depends": [],
   "backend": {
     "type": "cuda",
     "archs": [
       "11.0a"
     ]
   },
   "digest": {
     "algorithm": "sha256",
     "files": {
+      "__init__.py": "/6Ld6WSyL7PjILcYt4P7x3fnXi2C+ovbSP/7nNFetb8=",
+      "_adaptive_layernorm_producers_cuda_8a66d8b.abi3.so": "t6LbLgB9vIDaJiwgaJEFjH24wcfySbkq1hhcHOEbgU8=",
+      "_ops.py": "8CjL8CxdQouAOnaox+O0AKwLERGSDc8mao+V3ArMuTk=",
       "adaptive_layernorm_producers/__init__.py": "v6p5XMfQzddhi1fLSAw4HX9CyS0rQsidvu9VsT01xi4="
     }
   },
   "provenance": {
     "kernel": {
+      "sha": "8a66d8b",
       "dirty": false
     }
   }
 }