Update torch211-cxx11-cu130-aarch64-linux from source 92c4b99

Browse files

Files changed (4) hide show

build/torch211-cxx11-cu130-aarch64-linux/__init__.py +195 -0
build/torch211-cxx11-cu130-aarch64-linux/_fp4_gemm_cuda_92c4b99.abi3.so +3 -0
build/torch211-cxx11-cu130-aarch64-linux/_ops.py +3 -3
build/torch211-cxx11-cu130-aarch64-linux/metadata.json +9 -5

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

@@ -42,6 +42,16 @@ def _linear_fp16_fake(a_packed, b_packed, sfa, sfb, out, alpha: float = 1.0, var
     return None
 @torch.library.register_fake(add_op_namespace_prefix("nvfp4_gemm_geglu_nvfp4_fp16"))
 def _geglu_fp4_fake(a, b, sfa, sfb, scratch, out_packed, out_sfa, skinny: bool = False) -> None:
     return None
@@ -94,6 +104,16 @@ def _quant_fake(x: torch.Tensor, packed: torch.Tensor, sfa: torch.Tensor, is_sfb
     return None
 @torch.library.register_fake(add_op_namespace_prefix("quantize_e0m3_sfa_fp16"))
 def _quant_e0m3_fake(x, packed, sfa, is_sfb: bool = False) -> None:
     return None
@@ -158,6 +178,104 @@ def quantize_fp4_sfa_fp16(
     return packed, sfa
 def quantize_e0m3_sfa_fp16(
     x: torch.Tensor,
     packed: torch.Tensor | None = None,
@@ -276,6 +394,52 @@ def nvfp4_gemm_fp16(
     return out
 def nvfp4_gemm_geglu_nvfp4_fp16(
     a_packed: torch.Tensor,
     b_interleaved_packed: torch.Tensor,
@@ -307,6 +471,29 @@ def nvfp4_gemm_geglu_nvfp4_fp16(
     return out_packed, out_sfa
 def nvfp4_gemm_bias_gelu_nvfp4_fp16(
     a_packed: torch.Tensor,
     b_packed: torch.Tensor,
@@ -527,12 +714,16 @@ def nvfp4_gemm_streamk_bias_bf16(
 __all__ = [
     "dequantize_fp4_sfa_fp16",
     "e0m3_weight_gemm_fp16",
     "fp4_w4a16_linear_bf16",
     "fp4_w4a4_gemv_warpsplit_bf16",
     "nvfp4_gemm_bf16",
     "nvfp4_gemm_fp16",
     "nvfp4_gemm_geglu_nvfp4_fp16",
     "nvfp4_gemm_bias_gelu_nvfp4_fp16",
     "nvfp4_gemm_bias_residual_fp16",
@@ -545,6 +736,10 @@ __all__ = [
     "nvfp4_gemm_streamk_bf16",
     "nvfp4_gemm_streamk_bias_bf16",
     "quantize_fp4_sfa_fp16",
     "quantize_e0m3_sfa_fp16",
     "quantize_fp4_sfa_bf16",
     "sfa_size_bytes",

     return None
+@torch.library.register_fake(add_op_namespace_prefix("nvfp4_gemm_variant_bf16"))
+def _linear_variant_bf16_fake(a, b, sfa, sfb, out, alpha: float = 1.0, variant: int = 7) -> None:
+    return None
+@torch.library.register_fake(add_op_namespace_prefix("nvfp4_gemm_nvfp4"))
+def _linear_fp4out_fake(a, b, sfa, sfb, out_packed, out_sfa) -> None:
+    return None
 @torch.library.register_fake(add_op_namespace_prefix("nvfp4_gemm_geglu_nvfp4_fp16"))
 def _geglu_fp4_fake(a, b, sfa, sfb, scratch, out_packed, out_sfa, skinny: bool = False) -> None:
     return None
     return None
+@torch.library.register_fake(add_op_namespace_prefix("quantize_fp4_sfa_mse_fp16"))
+def _quant_mse_fake(x, packed, sfa, is_sfb: bool = False) -> None:
+    return None
+@torch.library.register_fake(add_op_namespace_prefix("quantize_fp4_sfa_mse_bf16"))
+def _quant_mse_bf16_fake(x, packed, sfa, is_sfb: bool = False) -> None:
+    return None
 @torch.library.register_fake(add_op_namespace_prefix("quantize_e0m3_sfa_fp16"))
 def _quant_e0m3_fake(x, packed, sfa, is_sfb: bool = False) -> None:
     return None
     return packed, sfa
+def quantize_fp4_sfa_mse_fp16(
+    x: torch.Tensor,
+    packed: torch.Tensor | None = None,
+    sfa: torch.Tensor | None = None,
+    is_sfb: bool = False,
+):
+    """Pack FP16 weights using per-block reconstruction-MSE scale search."""
+    if packed is None or sfa is None:
+        packed, sfa = _alloc_fp4(x.shape[0], x.shape[1], x.device)
+    ops.quantize_fp4_sfa_mse_fp16(x, packed, sfa, bool(is_sfb))
+    return packed, sfa
+def quantize_fp4_sfa_mse_bf16(
+    x: torch.Tensor,
+    packed: torch.Tensor | None = None,
+    sfa: torch.Tensor | None = None,
+    is_sfb: bool = False,
+):
+    """Pack BF16 weights using per-block reconstruction-MSE scale search."""
+    if packed is None or sfa is None:
+        packed, sfa = _alloc_fp4(x.shape[0], x.shape[1], x.device)
+    ops.quantize_fp4_sfa_mse_bf16(x, packed, sfa, bool(is_sfb))
+    return packed, sfa
+def aligned_fp4_dim(dim: int, alignment: int = 32) -> int:
+    """Return the physical FP4 GEMM dimension for a logical dimension."""
+    if dim <= 0 or alignment <= 0 or alignment % 16 != 0:
+        raise ValueError("dim must be positive and alignment divisible by 16")
+    return ((dim + alignment - 1) // alignment) * alignment
+def quantize_fp4_sfa_padded_bf16(
+    x: torch.Tensor,
+    *,
+    alignment: int = 32,
+    is_sfb: bool = False,
+):
+    """Bind-time BF16 pack with zero padding on the final dimension.
+    The returned packed tensor uses the physical aligned width. Keep the
+    logical width returned as the third item for slicing final model outputs.
+    This helper allocates and is intentionally not a runtime hot-path op.
+    """
+    if x.ndim != 2 or x.dtype != torch.bfloat16:
+        raise ValueError("x must be a 2-D BF16 tensor")
+    logical_dim = int(x.shape[1])
+    physical_dim = aligned_fp4_dim(logical_dim, alignment)
+    if physical_dim == logical_dim:
+        padded = x.contiguous()
+    else:
+        padded = torch.zeros(
+            (x.shape[0], physical_dim), device=x.device, dtype=x.dtype
+        )
+        padded[:, :logical_dim].copy_(x)
+    packed, sfa = quantize_fp4_sfa_bf16(padded, is_sfb=is_sfb)
+    return packed, sfa, logical_dim
+def pack_nvfp4_weight_bf16(
+    weight: torch.Tensor,
+    bias: torch.Tensor | None = None,
+    *,
+    alignment: int = 32,
+    mse: bool = False,
+):
+    """Zero-pad and pack a logical ``(N, K)`` BF16 weight at bind time.
+    Both physical ``N`` and ``K`` are aligned. This is the model-neutral
+    contract used by widths such as SigLIP's logical 4304, which becomes 4320
+    for Blackwell NVFP4 TMA. The hot path consumes the returned static tensors
+    directly and performs no padding or allocation.
+    """
+    if weight.ndim != 2 or weight.dtype != torch.bfloat16:
+        raise ValueError("weight must be a 2-D BF16 tensor")
+    logical_n, logical_k = map(int, weight.shape)
+    physical_n = aligned_fp4_dim(logical_n, alignment)
+    physical_k = aligned_fp4_dim(logical_k, alignment)
+    padded_weight = torch.zeros(
+        (physical_n, physical_k), device=weight.device, dtype=weight.dtype
+    )
+    padded_weight[:logical_n, :logical_k].copy_(weight)
+    quantize = quantize_fp4_sfa_mse_bf16 if mse else quantize_fp4_sfa_bf16
+    packed, sfb = quantize(padded_weight, is_sfb=True)
+    padded_bias = None
+    if bias is not None:
+        if bias.ndim != 1 or bias.numel() != logical_n:
+            raise ValueError("bias must have shape (N,)")
+        if bias.dtype != torch.bfloat16 or bias.device != weight.device:
+            raise ValueError("bias must match the weight dtype and device")
+        padded_bias = torch.zeros(
+            (physical_n,), device=bias.device, dtype=bias.dtype
+        )
+        padded_bias[:logical_n].copy_(bias)
+    return packed, sfb, padded_bias, (logical_n, logical_k)
 def quantize_e0m3_sfa_fp16(
     x: torch.Tensor,
     packed: torch.Tensor | None = None,
     return out
+def nvfp4_gemm_variant_bf16(
+    a_packed: torch.Tensor,
+    b_packed: torch.Tensor,
+    sfa: torch.Tensor,
+    sfb: torch.Tensor,
+    alpha: float = 1.0,
+    out: torch.Tensor | None = None,
+    variant: int = 7,
+) -> torch.Tensor:
+    """SM110 native NVFP4 GEMM with BF16 output.
+    ``variant=7`` serves large-M encoder/SigLIP shapes; ``variant=10`` is
+    the narrow-N PI0.5 decoder tile. The indices match FlashRT native.
+    """
+    if out is None:
+        out = torch.empty(
+            (a_packed.shape[0], b_packed.shape[0]),
+            device=a_packed.device,
+            dtype=torch.bfloat16,
+        )
+    ops.nvfp4_gemm_variant_bf16(
+        a_packed, b_packed, sfa, sfb, out, float(alpha), int(variant)
+    )
+    return out
+def nvfp4_gemm_nvfp4(
+    a_packed: torch.Tensor,
+    b_packed: torch.Tensor,
+    sfa: torch.Tensor,
+    sfb: torch.Tensor,
+    *,
+    out_packed: torch.Tensor | None = None,
+    out_sfa: torch.Tensor | None = None,
+) -> tuple[torch.Tensor, torch.Tensor]:
+    """SM110 NVFP4 GEMM with an NVFP4 output and CUTLASS SFA layout."""
+    if out_packed is None or out_sfa is None:
+        out_packed, out_sfa = _alloc_fp4(
+            a_packed.shape[0], b_packed.shape[0], a_packed.device
+        )
+    ops.nvfp4_gemm_nvfp4(
+        a_packed, b_packed, sfa, sfb, out_packed, out_sfa
+    )
+    return out_packed, out_sfa
 def nvfp4_gemm_geglu_nvfp4_fp16(
     a_packed: torch.Tensor,
     b_interleaved_packed: torch.Tensor,
     return out_packed, out_sfa
+def cutlass_fp4_gemm_geglu_il_hw_v10(
+    a_packed: torch.Tensor,
+    b_interleaved_packed: torch.Tensor,
+    sfa: torch.Tensor,
+    sfb: torch.Tensor,
+    *,
+    scratch: torch.Tensor | None = None,
+    out_packed: torch.Tensor | None = None,
+    out_sfa: torch.Tensor | None = None,
+) -> tuple[torch.Tensor, torch.Tensor]:
+    """Explicit public alias for the native SM110 v10 GeGLU schedule."""
+    return nvfp4_gemm_geglu_nvfp4_fp16(
+        a_packed,
+        b_interleaved_packed,
+        sfa,
+        sfb,
+        skinny=True,
+        scratch=scratch,
+        out_packed=out_packed,
+        out_sfa=out_sfa,
+    )
 def nvfp4_gemm_bias_gelu_nvfp4_fp16(
     a_packed: torch.Tensor,
     b_packed: torch.Tensor,
 __all__ = [
+    "aligned_fp4_dim",
+    "cutlass_fp4_gemm_geglu_il_hw_v10",
     "dequantize_fp4_sfa_fp16",
     "e0m3_weight_gemm_fp16",
     "fp4_w4a16_linear_bf16",
     "fp4_w4a4_gemv_warpsplit_bf16",
     "nvfp4_gemm_bf16",
     "nvfp4_gemm_fp16",
+    "nvfp4_gemm_variant_bf16",
+    "nvfp4_gemm_nvfp4",
     "nvfp4_gemm_geglu_nvfp4_fp16",
     "nvfp4_gemm_bias_gelu_nvfp4_fp16",
     "nvfp4_gemm_bias_residual_fp16",
     "nvfp4_gemm_streamk_bf16",
     "nvfp4_gemm_streamk_bias_bf16",
     "quantize_fp4_sfa_fp16",
+    "quantize_fp4_sfa_mse_fp16",
+    "quantize_fp4_sfa_mse_bf16",
+    "quantize_fp4_sfa_padded_bf16",
+    "pack_nvfp4_weight_bf16",
     "quantize_e0m3_sfa_fp16",
     "quantize_fp4_sfa_bf16",
     "sfa_size_bytes",

build/torch211-cxx11-cu130-aarch64-linux/_fp4_gemm_cuda_92c4b99.abi3.so ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa36d417fac09d8ed49fbb867c35562ed06ca80b67747c09624406e21afcd38e
+size 6002944

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

@@ -1,6 +1,6 @@
 import torch
-from . import _fp4_gemm_cuda_230e467
-ops = torch.ops._fp4_gemm_cuda_230e467
 def add_op_namespace_prefix(op_name: str):
-    return f"_fp4_gemm_cuda_230e467::{op_name}"

 import torch
+from . import _fp4_gemm_cuda_92c4b99
+ops = torch.ops._fp4_gemm_cuda_92c4b99
 def add_op_namespace_prefix(op_name: str):
+    return f"_fp4_gemm_cuda_92c4b99::{op_name}"

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

@@ -1,6 +1,6 @@
 {
   "name": "fp4-gemm",
-  "id": "_fp4_gemm_cuda_230e467",
   "version": 1,
   "license": "Apache-2.0",
   "python-depends": [],
@@ -13,16 +13,20 @@
   "digest": {
     "algorithm": "sha256",
     "files": {
-      "__init__.py": "Qfdvg/9EedWLGh34xAalDfC0IsAHCOL44L4ShaP/w5Y=",
-      "_fp4_gemm_cuda_230e467.abi3.so": "+S6jqUWDLr1zfPB06sSYNnT9ALFgr6FIHNJBSOjjIpc=",
-      "_ops.py": "IfU2iMVrWYRnoe6q8HI3hU8TPnAlLrXDerlv117PcXI=",
       "fp4_gemm/__init__.py": "v6p5XMfQzddhi1fLSAw4HX9CyS0rQsidvu9VsT01xi4="
     }
   },
   "provenance": {
     "kernel": {
-      "sha": "230e467",
       "dirty": false
     }
   }
 }

 {
   "name": "fp4-gemm",
+  "id": "_fp4_gemm_cuda_92c4b99",
   "version": 1,
   "license": "Apache-2.0",
   "python-depends": [],
   "digest": {
     "algorithm": "sha256",
     "files": {
+      "__init__.py": "Mr1/bAUzs+af68D+bRXX6iONDof//dzKgn6QU5pKdu8=",
+      "_fp4_gemm_cuda_92c4b99.abi3.so": "+jbUF/rAnY7Un7uGfDVWLtBsqAtndHwJYkQG4hr8044=",
+      "_ops.py": "twu0zeqTyaITBKAdr9FudRbkbXpvBQdmAHcVf/OXw2I=",
       "fp4_gemm/__init__.py": "v6p5XMfQzddhi1fLSAw4HX9CyS0rQsidvu9VsT01xi4="
     }
   },
   "provenance": {
     "kernel": {
+      "sha": "92c4b991b6f1fbd89744aa6f46f62b1bfac7ca7e",
       "dirty": false
+    },
+    "validation": {
+      "torch": "2.11.0+cu130",
+      "cuda": "13.0"
     }
   }
 }