feat: expand torch op allowlist

Author: voltjia

scripts/torch_ops.yaml

@@ -13,8 +13,11 @@
 - acosh
 - adaptive_avg_pool2d
 - adaptive_avg_pool3d
+- adaptive_avg_pool3d_backward
 - adaptive_max_pool2d
+- adaptive_max_pool2d_backward
 - adaptive_max_pool3d
+- adaptive_max_pool3d_backward
 - add
 - addbmm
 - addcdiv
@@ -44,11 +47,14 @@
 - atan2
 - atanh
 - avg_pool2d
+- avg_pool2d_backward
 - avg_pool3d
+- avg_pool3d_backward
 - baddbmm
 - batch_norm_elemt
 - bernoulli
 - binary_cross_entropy
+- binary_cross_entropy_backward
 - bitwise_and
 - bitwise_left_shift
 - bitwise_not
@@ -85,6 +91,7 @@
 - divide
 - dot
 - elu
+- elu_backward
 - empty
 - eq
 - erf
@@ -122,22 +129,32 @@
 - fmin
 - fmod
 - frac
+- fractional_max_pool2d
+- fractional_max_pool2d_backward
+- fractional_max_pool3d
+- fractional_max_pool3d_backward
 - frexp
 - frobenius_norm
 - full
 - gather
 - gcd
 - ge
 - gelu
+- gelu_backward
+- geqrf
 - ger
 - glu
+- glu_backward
 - greater
 - greater_equal
 - gt
 - hardshrink
+- hardshrink_backward
 - hardsigmoid
+- hardsigmoid_backward
 - hardswish
 - hardtanh
+- hardtanh_backward
 - heaviside
 - histc
 - histogram
@@ -165,19 +182,23 @@
 - ldexp
 - le
 - leaky_relu
+- leaky_relu_backward
 - lerp
 - less
 - less_equal
 - lgamma
 - linalg_cholesky
+- linalg_cholesky_ex
 - linalg_cond
 - linalg_cross
 - linalg_det
 - linalg_eig
+- linalg_eigh
 - linalg_eigvals
 - linalg_eigvalsh
 - linalg_householder_product
 - linalg_inv
+- linalg_inv_ex
 - linalg_ldl_factor
 - linalg_ldl_factor_ex
 - linalg_ldl_solve
@@ -197,6 +218,7 @@
 - linalg_solve
 - linalg_solve_ex
 - linalg_solve_triangular
+- linalg_svd
 - linalg_svdvals
 - linalg_tensorinv
 - linalg_tensorsolve
@@ -209,6 +231,8 @@
 - log1p
 - log2
 - log_sigmoid
+- log_sigmoid_backward
+- log_sigmoid_forward
 - log_softmax
 - logaddexp
 - logaddexp2
@@ -218,6 +242,7 @@
 - logical_or
 - logical_xor
 - logit
+- logit_backward
 - logspace
 - logsumexp
 - lt
@@ -228,28 +253,36 @@
 - matrix_power
 - max
 - max_pool2d_with_indices
+- max_pool2d_with_indices_backward
 - max_pool3d_with_indices
+- max_pool3d_with_indices_backward
 - max_unpool2d
 - max_unpool3d
 - maximum
 - mean
+- median
 - min
-- mode
 - minimum
 - mish
 - mkldnn_adaptive_avg_pool2d
 - mm
+- mode
 - mse_loss
+- mse_loss_backward
 - msort
 - mul
 - multi_margin_loss
+- multi_margin_loss_backward
 - multilabel_margin_loss
+- multilabel_margin_loss_backward
+- multilabel_margin_loss_forward
 - multinomial
 - multiply
 - mv
 - mvlgamma
 - nan_to_num
 - nanmean
+- nanmedian
 - nanquantile
 - nansum
 - narrow_copy
@@ -260,6 +293,10 @@
 - nextafter
 - nll_loss
 - nll_loss2d
+- nll_loss2d_backward
+- nll_loss2d_forward
+- nll_loss_backward
+- nll_loss_forward
 - nonzero
 - nonzero_static
 - norm
@@ -274,6 +311,7 @@
 - polygamma
 - pow
 - prod
+- qr
 - quantile
 - rad2deg
 - rand
@@ -283,13 +321,19 @@
 - range
 - reciprocal
 - reflection_pad1d
+- reflection_pad1d_backward
 - reflection_pad2d
+- reflection_pad2d_backward
 - reflection_pad3d
+- reflection_pad3d_backward
 - remainder
 - renorm
 - replication_pad1d
+- replication_pad1d_backward
 - replication_pad2d
+- replication_pad2d_backward
 - replication_pad3d
+- replication_pad3d_backward
 - round
 - rrelu_with_noise
 - rsqrt
@@ -299,21 +343,29 @@
 - searchsorted
 - sgn
 - sigmoid
+- sigmoid_backward
 - sign
 - signbit
 - silu
+- silu_backward
 - sin
 - sinc
 - sinh
 - slogdet
 - slow_conv3d
+- slow_conv3d_forward
 - slow_conv_transpose2d
 - slow_conv_transpose3d
 - smooth_l1_loss
+- smooth_l1_loss_backward
 - soft_margin_loss
+- soft_margin_loss_backward
 - softmax
 - softplus
+- softplus_backward
 - softshrink
+- softshrink_backward
+- sort
 - sparse_sampled_addmm
 - special_airy_ai
 - special_bessel_j0
@@ -378,26 +430,39 @@
 - sub
 - subtract
 - sum
+- svd
 - take
 - take_along_dim
 - tan
 - tanh
+- tanh_backward
 - tensordot
 - thnn_conv2d
 - threshold
+- threshold_backward
+- topk
+- triangular_solve
 - tril
 - triu
 - true_divide
 - trunc
 - unbind_copy
 - upsample_bicubic2d
+- upsample_bicubic2d_backward
 - upsample_bilinear2d
+- upsample_bilinear2d_backward
 - upsample_linear1d
+- upsample_linear1d_backward
 - upsample_nearest1d
+- upsample_nearest1d_backward
 - upsample_nearest2d
+- upsample_nearest2d_backward
 - upsample_nearest3d
+- upsample_nearest3d_backward
 - upsample_trilinear3d
+- upsample_trilinear3d_backward
 - var
 - vdot
 - where
+- xlogy
 - zeros