ȅiE*SSKJr SSKJrJr SSKJrJrJrJ r SSK r SSK r SSK J r SSKJr SSK JrJrJr \(a SS KJr SSKr"S S \5r"S S \5rg)) annotations)ABCabstractmethod)AnyOptional TYPE_CHECKINGUnionN)ir)V) FixedLayoutFlexibleLayoutLayout)Sequencec\rSrSrSrSSSjjrSSSjjr\SSj5r\SSj5r SSjr SS jr SS jr SS jr SS jrSS jrSSjrSS Sjjr\S!Sj5rS"Sjr\S#S$Sjj5rSrg)% KernelInputsz Class to store and provide access to input nodes for kernels. This class takes in a tuple of input nodes and provides methods to access information about these nodes, such as their device type and device. NcnXlSUlUbUO0UlX0l[ U5S:dS5eg)z Initialize with a tuple of input nodes. Args: input_nodes: A tuple of input nodes to store out_dtype: Optional output dtype to store Nrz Expected at least one input node) _input_nodes _device_name_scalars _out_dtypelen)self input_nodesscalars out_dtypes W/home/james-whalen/.local/lib/python3.13/site-packages/torch/_inductor/kernel_inputs.py__init__KernelInputs.__init__s>(+/#*#6B #;!#G%GG#cUc UR$[UR5[U5:Xd)S[UR5S[U535eUVs/sHo RUPM sn$s snf)z Return the stored input nodes, optionally reordered. Args: reorder: Optional sequence of indices to reorder the nodes. For example, (2, 0, 1) would return nodes in that order. Returns: The tuple of input nodes, optionally reordered zReorder length mismatch:  vs )rr)rreorderis rnodesKernelInputs.nodes.s| ?$$ $4$$%W5 'D,=,=(>'?tCL> R 5/66g!!!$g666sA:c,[UR5$)zH Get the number of input nodes. Returns: The number of input nodes )rrrs rcountKernelInputs.count@s4$$%%r!cH[R"URS5$)z\ Get the device type of the first node. Returns: The device type (e.g., 'cuda', 'cpu') r)r get_device_typerr)s r device_typeKernelInputs.device_typeJs !!$"3"3A"677r!c<URSR5$)zN Get the device of the first node. Returns: The device of the first node r)r get_devicer)s rdeviceKernelInputs.deviceUs  #..00r!cURcPUR5nURS:Xa0[RR U5nUR UlUR$)zU Get the device name information. Returns: A tuple of (gpu_name, vendor, model) cuda)rr2r.torchr5get_device_properties gcnArchName)rr2device_propertiess r device_nameKernelInputs.device_name^sX    $[[]F6)$)JJ$D$DV$L!$5$A$A!   r!c:[SUR55$)zg Get the symbolic shapes of all input nodes. Returns: A tuple of shape tuples for each input node c3@# UHoR5v M g7fN)get_size.0nodes r /KernelInputs.shapes_symbolic..ssC1B]]__1Btuplerr)s rshapes_symbolicKernelInputs.shapes_symboliclsC1B1BCCCr!c:[SUR55$)z Get the size hints for shapes of all input nodes. Returns: A tuple of shape tuples with integer hints for each input node c3# UH]n[RRRUR 5[ R RRS9v M_ g7f)fallbackN) r graphsizevars size_hintsr?r6 _inductorconfigunbacked_symint_fallbackr@s rrC-KernelInputs.shapes_hinted..|sQ * GG   ' ' //HH ( *A%A'rFr)s r shapes_hintedKernelInputs.shapes_hintedu& ))    r!c:[SUR55$)zi Get the symbolic strides of all input nodes. Returns: A tuple of stride tuples for each input node c3@# UHoR5v M g7fr>) get_strider@s rrC0KernelInputs.strides_symbolic..sE3D4__&&3DrErFr)s rstrides_symbolicKernelInputs.strides_symbolicsE43D3DEEEr!c:[SUR55$)z Get the size hints for strides of all input nodes. Returns: A tuple of stride tuples with integer hints for each input node c3# UH]n[RRRUR 5[ R RRS9v M_ g7frL) r rNrOrPr[r6rQrRrSr@s rrC.KernelInputs.strides_hinted..sR * GG   ' '!//HH ( *rUrFr)s rstrides_hintedKernelInputs.strides_hintedrXr!c:[SUR55$)zX Get the dtypes of all input nodes. Returns: A tuple of dtypes for each input node c3@# UHoR5v M g7fr>) get_dtyper@s rrC&KernelInputs.dtypes..sD2C$^^%%2CrErFr)s rdtypesKernelInputs.dtypessD$2C2CDDDr!c<URUR5$)z Get the dtype of a specific input node. Args: idx: Index of the node to get the dtype from (default: 0) Returns: The dtype of the specified input node )rrf)ridxs rdtypeKernelInputs.dtypes  %//11r!cg)c Get the output dtype, whether passed in or inferred from the nodes Returns: The output dtype Nr)s rrKernelInputs.out_dtyper!cTXR;d SUS35eURU$)zr Get the scalar value for a given name. Args: name: Name of the scalar to get Returns: The scalar value zScalar z not found, but required)r)rnames r get_scalarKernelInputs.get_scalars2}}$Nv5M&NN$}}T""r!cg)z Abstract method to handle output layout generation. Args: out_dtype: Optional output dtype. If not provided, infer from inputs flexible: If True, return FlexibleLayout, otherwise FixedLayout Nrp)rflexibles r output_layoutKernelInputs.output_layoutrrr!)rrrr)NN)r list[Any]r&Optional[dict[str, Union[float, int]]]rOptional[torch.dtype]r>)r$zOptional[Sequence[int]]returnr{)r~int)r~z Optional[str])r~z torch.device)r~ztuple[tuple[Any, ...], ...])r~ztuple[tuple[int, ...], ...])r~z%tuple[tuple[sympy.Integer, ...], ...])r~ztuple[torch.dtype, ...])r)rkrr~ torch.dtyper~r)rtstrr~zUnion[float, int]Trxboolr~r)__name__ __module__ __qualname____firstlineno____doc__rr&propertyr*r.r2r:rHrVr]rbrhrlrrrury__static_attributes__rpr!rrrs;?+/ HH8H) H&7$&&881 !D  F  E 2   #  r!rc^\rSrSrSrS S U4SjjjrS SjrS SjrSSSjjrSSjr SSjr S r U=r $)MMKernelInputszz Specialized KernelInputs for matrix multiplication operations. Provides additional methods to access M, N, K dimensions. cZ>[TU]XU5 [UR5S:dS5eXEpvUS:aU[U5- nUS:aU[U5- nSUs=::a[U5:d O SU35eSUs=::a[U5:d O SU35eX@lXPlg)z Initialize with a tuple of input nodes. By default, we assume the last 2 input nodes are mat1 and mat2, but the caller can adjust when necessary zExpected at least 2 input nodesrzInvalid mat1_idx: zInvalid mat2_idx: N)superrrr _mat1_idx _mat2_idx) rrrrmat1_idxmat2_idxm1_idxm2_idx __class__s rrMMKernelInputs.__init__s y94$$%*M,MM*" a< c+& &F a< c+& &FF-S--N1CH:/NN-F-S--N1CH:/NN-!!r!chUR5URnUR5URnUR5SnUR5SnUR5SnUR5Sn[R R RXF5 X5U4$)aq Get the symbolic M, N, K dimensions for matrix multiplication. Handles both 2D (MM) and 3D (BMM) tensors. M is extracted from the second-to-last dimension of the first operand (mat1). N is extracted from the last dimension of the second operand (mat2). K is extracted from the last dimension of the first operand (mat1). Returns: A tuple of (M, N, K) dimensions )r&rrr?r rNrO check_equals)rmat1mat2mknk0s r mnk_symbolicMMKernelInputs.mnk_symbolicszz|DNN+zz|DNN+ MMOB  MMOB  MMOB ]]_R  %%a,ayr!cvURb UR$UR5SR5$)ror)rmat1mat2rfr)s rrMMKernelInputs.out_dtypes2 ?? &?? "}}q!++--r!cUR5up#UR5nUR5GtpVnUR5Gtpn [XX5V V s/sH.up[R R RX5PM0 sn n n /U QUPU Pn U(a[UR5XM5$[UR5XM5$s sn n f)z Handle output layout generation for matrix multiplication. Args: out_dtype: Optional output dtype. If not provided, infer from inputs flexible: If True, return FlexibleLayout, otherwise FixedLayout ) rrr?zipr rNrOcheck_equals_and_simplifyrr2r )rrxrrrb1rk1b2k2rabsizes rryMMKernelInputs.output_layouts]]_ NN$ ]]_ ]]_ JMb+ V+$!QWW   7 7 =+ VzAzqz !$++-A At{{}i> > Ws5CcZUR5nXRXR4$)zJ Get the mat1 and mat2 nodes. Returns: A tuple of (mat1, mat2) nodes )r&rr)rr&s rrMMKernelInputs.mat1mat22s( ^^$eNN&;;;r!cUR5nXRnXRnUSnUSnUSnUSnXW:Xd SUSU35eXFU4$)z Get the hinted M, N, K dimensions for matrix multiplication. Handles both 2D (MM) and 3D (BMM) tensors. Uses shapes_hinted from the base class to get integer hints for dimensions. Returns: A tuple of (M, N, K) dimensions as integers rrzK dimensions don't match: r#)rVrr)r hinted_shapes mat1_shape mat2_shaperrrk_checks r mnk_hintedMMKernelInputs.mnk_hinted<sw**, ">>2 ">>2 rN rN rNR.|J9!D JJ|ayr!)rr)NNrr) rr{rr|rr}rrrr)r~z2tuple[sympy.Integer, sympy.Integer, sympy.Integer]rrr)r~ztuple[Any, Any])r~ztuple[int, int, int]) rrrrrrrrryrrr __classcell__)rs@rrrsw;?+/ ""8") "  "  ""B ;4 .?(<r!r) __future__rabcrrtypingrrrr r6torch._inductor.configtorch._inductorr torch._inductor.virtualizedr r rrcollections.abcrsympyrrrpr!rrsK"#66 )33({ 3{ |@\@r!