
    i}                     $   U d dl Z d dlmZmZmZ ddlmZ d dlmZm	Z	m
Z
mZmZ d dlmZ d dlmZ d dlmZ d d	lmZ d d
lmZ d dlmZ d dlZddgZ ed      Z ed      Ze j:                  j<                  Zd Zi Z e!eef   e"d<   d Z#d:deeeef   geeef   f   fdZ$ e$ejJ                        ddde&fd       Z' e$ejP                        d;de&fd       Z) e$ejT                        d;de&fd       Z+ e$ejX                        d;de&fd       Z- e$ej\                        	 	 	 	 	 d<de&fd       Z/	 d:de0e&   de0e&   de0e&   de1de&f
dZ2 e$ejf                  ejh                  ejj                  ejl                  g      ddde&fd        Z7 e$ejp                        de&fd!       Z9d" Z: e$ejv                  ejx                  ejz                  g      ddde&fd#       Z>d$ Z?dd%dee@e@e&d&f   e@e&d&f   e@e&d&f   e	e@e&d&f      f      fd'ZAdd%dee@e@e&d&f   e@e&d&f   e@e&d&f   e	e@e&d&f      f      fd(ZB e$ej                  d)*      ddde&fd+       ZD e$ej                  d)*      de&fd,       ZFd- ZG e$ej                  ej                  ej                  g      ddde&fd.       ZK e$ej                  d)*      de&fd/       ZM e$ej                  d)*      de&fd0       ZOi ejJ                  e'ejP                  e)ejT                  e+ejX                  e-ej\                  e/ejf                  e7ejh                  e7ejj                  e7ejl                  e7ejp                  e9ejv                  e>ejx                  e>ejz                  e>ej                  eKej                  eKej                  eKej                  eDej                  eFej                  eMej                  eOiZ d1 ZPg d2ZQd3 ZRd4 ZSd5 ZTd6 ZU G d7 d      ZV G d8 d9e      ZWy)=    N)tree_maptree_flattentree_unflatten   )ModuleTracker)AnyOptionalUnionTypeVarCallable)Iterator)	ParamSpec)defaultdict)TorchDispatchModeprodwrapsFlopCounterModeregister_flop_formula_T_Pc                 R    t        | t        j                        r| j                  S | S N)
isinstancetorchTensorshape)is    R/var/www/html/engine/venv/lib/python3.12/site-packages/torch/utils/flop_counter.py	get_shaper!      s    !U\\"wwH    flop_registryc                 4     t               d d fd
       }|S )N)out_valc                 F    t        t        ||| f      \  }}} |d|i|S )N	out_shape)r   r!   )r%   argskwargsr'   fs       r    nfzshape_wrapper.<locals>.nf   s2    "*9tVW6M"Nfi$6)6v66r"   r   r*   r+   s   ` r    shape_wrapperr-      s#    
1X 7 7 Ir"   returnc                 d     dt         t        t        f   dt         t        t        f   f fd}|S )Nflop_formular.   c                      st                 fd}t        j                  j                  j	                  |        S )Nc                     t        | t        j                  j                        st	        d|  dt        |              | t        v rt        d|        t        | <   y )Nzlregister_flop_formula(targets): expected each target to be OpOverloadPacket (i.e. torch.ops.mylib.foo), got z which is of type zduplicate registrations for )r   r   _opsOpOverloadPacket
ValueErrortyper#   RuntimeError)targetr0   s    r    registerz=register_flop_formula.<locals>.register_fun.<locals>.register(   si    fejj&A&AB Hh0f@A A &"%A&#JKK$0M&!r"   )r-   r   utils_pytree	tree_map_)r0   r9   get_rawtargetss   ` r    register_funz+register_flop_formula.<locals>.register_fun$   s7    (6L	1 	%%h8r"   )r   r   r   )r>   r=   r?   s   `` r    r   r   #   s0    8BF#3 R8H & r"   )r'   c                :    | \  }}|\  }}||k(  sJ ||z  dz  |z  S )zCount flops for matmul.    )	a_shapeb_shaper'   r(   r)   mkk2ns	            r    mm_floprI   9   s3    
 DAqEB7N7q519q=r"   c                     t        ||      S )zCount flops for addmm.rI   
self_shaperC   rD   r'   r)   s        r    
addmm_floprN   D   s     7G$$r"   c                 V    | \  }}}|\  }}}	||k(  sJ ||k(  sJ ||z  |	z  dz  |z  }
|
S )z"Count flops for the bmm operation.rA   rB   )rC   rD   r'   r)   brE   rF   b2rG   rH   flops              r    bmm_floprS   I   sK    
 GAq!IBA7N77N7q519q=1DKr"   c                     t        ||      S )z&Count flops for the baddbmm operation.rS   rL   s        r    baddbmm_floprV   V   s    
 GW%%r"   c	                     t        | |      S )zCount flops for _scaled_mm.rK   )
rC   rD   scale_a_shapescale_b_shape
bias_shapescale_result_shape	out_dtypeuse_fast_accumr'   r)   s
             r    _scaled_mm_flopr^   ]   s     7G$$r"   x_shapew_shaper'   
transposedc                 t    | d   }|r| n|dd }|^}}}	 t        |      t        |      z  |z  |z  |z  dz  }	|	S )a  Count flops for convolution.

    Note only multiplication is
    counted. Computation for bias are ignored.
    Flops for a transposed convolution are calculated as
    flops = (x_shape[2:] * prod(w_shape) * batch_size).
    Args:
        x_shape (list(int)): The input shape before convolution.
        w_shape (list(int)): The filter shape.
        out_shape (list(int)): The output shape after convolution.
        transposed (bool): is the convolution transposed
    Returns:
        int: the number of flops
    r   rA   Nr   )
r_   r`   r'   ra   
batch_size
conv_shapec_outc_infilter_sizerR   s
             r    conv_flop_countrh   n   s]    ( J''Y;J 'E4+ 
d;//*<uDtKaODKr"   c                     t        | |||      S )zCount flops for convolution.ra   )rh   )
r_   r`   _bias_stride_padding	_dilationra   r'   r(   r)   s
             r    	conv_flopro      s     7GY:NNr"   c                    d }d}	 |
d   r t        |d         }|t        | |||       z  }|
d   rZt        |d         }|r&|t         ||        ||       ||      d      z  }|S |t         ||       ||        ||      d      z  }|S )Nc                 4    | d   | d   gt        | dd        z   S )Nr   r   rA   )list)r   s    r    tzconv_backward_flop.<locals>.t   s$    a%(#d59o55r"   r   r   Frj   )r!   rh   )grad_out_shaper_   r`   rk   rl   rm   rn   ra   _output_padding_groupsoutput_maskr'   rs   
flop_countgrad_input_shapegrad_weight_shapes                   r    conv_backward_flopr{      s    6JDL 1~$Yq\2ong?OU_Q_``
1~%il3/!N*;QwZK\I]joppJ
  /!G*a6GK\I]joppJr"   c                     | \  }}}}|\  }}}	}
|\  }}}}||cxk(  r|k(  r"n J ||cxk(  r|k(  rn J ||
k(  r
|	|k(  r||
k(  sJ d}|t        ||z  ||f||z  ||	f      z  }|t        ||z  ||	f||z  |	|f      z  }|S )z^
    Count flops for self-attention.

    NB: We can assume that value_shape == key_shape
    r   rU   )query_shape	key_shapevalue_shaperP   hs_qd_q_b2_h2s_k_d2_b3_h3_s3d_vtotal_flopss                   r    sdpa_flop_countr     s     !NAq#s"Cc3$Cc3?s?[[qC3[[3#:#*QTX[Q[[[K8QUC-AsC/@AAK8QUC-AsC/@AAKr"   c                    t        | ||      S )Count flops for self-attention.r   )r}   r~   r   r'   r(   r)   s         r    	sdpa_flopr     s     ;	;??r"   c                     ddl m} ddlm} t	        | ||f      s7| j
                  j                  dk7  r| j                         j                         S |g| j                  d      dz
  z  S )z
    If the offsets tensor is fake, then we don't know the actual lengths.
    In that case, we can just assume the worst case; each batch has max length.
    r   )
FakeTensor)FunctionalTensormetar   )
torch._subclasses.fake_tensorr   #torch._subclasses.functional_tensorr   r   devicer6   difftolistsize)offsetsmax_lenr   r   s       r    _offsets_to_lengthsr     s[    
 9Dg
,<=>7>>CVCVZ`C`||~$$&&9Q!+,,r"   )grad_out.c              #   Z  K   |t        |j                        dk(  sJ t        |j                        dk(  sJ ||j                  | j                  k(  sJ | j                  \  }}	}
|j                  \  }}}|j                  \  }}}|J |J |j                  |j                  k(  sJ t        ||      }t        ||      }t        ||      D ]%  \  }}d|	||
f}d|||f}d|||f}||nd}||||f ' y| j                  |j                  |j                  ||j                  ndf yw)a;  
    Given inputs to a flash_attention_(forward|backward) kernel, this will handle behavior for
    NestedTensor inputs by effectively unbinding the NestedTensor and yielding the shapes for
    each batch element.

    In the case that this isn't a NestedTensor kernel, then it just yields the original shapes.
    N   r   lenr   r   zip)querykeyvaluer   	cum_seq_q	cum_seq_kmax_qmax_k_h_qr   h_kd_kh_vr   seq_q_lengthsseq_k_lengths	seq_q_len	seq_k_lennew_query_shapenew_key_shapenew_value_shapenew_grad_out_shapes                          r    %_unpack_flash_attention_nested_shapesr   )  s[    $  399~"""5;;1$$$8>>U[[#@@@kk3ii3kk3$$$$$$)//111+Iu=+Iu=&)-&G 	V"Y	 #y#6OY4M #y#6O4<4Hd!=/CUUU	V 	
++syy%++AUx~~[_
__s   D)D+c              #   `  K   |t        |j                        dk(  sJ t        |j                        dk(  sJ ||j                  | j                  k(  sJ | j                  \  }}}	}
|j                  \  }}}}|j                  \  }}}}|J |J |j                  |j                  k(  sJ t        ||      }t        ||      }t        ||      D ]%  \  }}d|	||
f}d|||f}d|||f}||nd}||||f ' y| j                  |j                  |j                  ||j                  ndf yw)a?  
    Given inputs to a efficient_attention_(forward|backward) kernel, this will handle behavior for
    NestedTensor inputs by effectively unbinding the NestedTensor and yielding the shapes for
    each batch element.

    In the case that this isn't a NestedTensor kernel, then it just yields the original shapes.
    N   r   r   )r   r   r   r   cu_seqlens_qcu_seqlens_kmax_seqlen_qmax_seqlen_kr   r   r   r   r   r   r   	seqlens_q	seqlens_klen_qlen_kr   r   r   r   s                          r    )_unpack_efficient_attention_nested_shapesr   W  sd    $  399~"""5;;1$$$8>>U[[#@@@1c31c31c3''''''!!\%7%7777'lC	'lC		95 	VLE5 #uc2OUC0M #uc2O4<4Hd!=/CUUU	V 	
++syy%++AUx~~[_
__s   D,D.T)r=   c          	      J    t        | ||||||      }
t        d |
D              S )r   )r   r   r   r   r   r   r   c              3   @   K   | ]  \  }}}}t        |||        y wr   r   .0r}   r~   r   r   s        r    	<genexpr>z0_flash_attention_forward_flop.<locals>.<genexpr>  )      2KK 	Y<   r   sum)r   r   r   r   r   r   r   r'   r(   r)   sizess              r    _flash_attention_forward_flopr     s?    " 2E  6;  r"   c           	      J    t        | ||||||      }
t        d |
D              S )r   )r   r   r   r   r   r   r   c              3   @   K   | ]  \  }}}}t        |||        y wr   r   r   s        r    r   z4_efficient_attention_forward_flop.<locals>.<genexpr>  r   r   r   r   )r   r   r   biasr   r   r   r   r(   r)   r   s              r    !_efficient_attention_forward_flopr     s?    " 6!!!!E  6;  r"   c                    d}|\  }}}}|\  }	}
}}|\  }}}}| \  }}}}||	cxk(  r|cxk(  r|k(  rn J ||
cxk(  r|cxk(  r|k(  r	n J ||k(  sJ ||k(  r
||k(  r||k(  sJ d}|t        ||z  ||f||z  ||f      z  }|t        ||z  ||f||z  ||f      z  }|t        ||z  ||f||z  ||f      z  }|t        ||z  ||f||z  ||f      z  }|t        ||z  ||f||z  ||f      z  }|S Nr   rU   )rt   r}   r~   r   r   rP   r   r   r   r   r   r   r   r   r   r   r   _b4_h4_s4_d4s                        r    sdpa_backward_flop_countr     sf   K NAq#s"Cc3$Cc3'Cc3!s!c!KKa3&<#&<&<KKKK#:#*33K 8QUC-AsC/@AAK 8QUC-AsC/@AAK8QUC-AsC/@AAK 8QUC-AsC/@AAK8QUC-AsC/@AAKr"   c                    t        | |||      S )z(Count flops for self-attention backward.r   )rt   r}   r~   r   r'   r(   r)   s          r    sdpa_backward_flopr     s    
 $NKKXXr"   c
           
      L    t        |||| ||||	      }t        d |D              S )N)r   r   r   r   r   r   r   r   c              3   B   K   | ]  \  }}}}t        ||||        y wr   r   r   r}   r~   r   rt   s        r    r   z1_flash_attention_backward_flop.<locals>.<genexpr>  +      ?KK 	!iU   r   )r   r   r   r   out	logsumexpr   r   r   r   r(   r)   shapess                r    _flash_attention_backward_flopr     sB    " 3	F  CI  r"   c
           
      L    t        |||| ||||	      }t        d |D              S )N)r   r   r   r   r   r   r   r   c              3   B   K   | ]  \  }}}}t        ||||        y wr   r   r   s        r    r   z5_efficient_attention_backward_flop.<locals>.<genexpr>%  r   r   r   )r   r   r   r   r   r   r   r   r   r   r(   r)   r   s                r    "_efficient_attention_backward_flopr   
  sB    " 7!!!!	F  CI  r"   c                 ,    t        | t              s| fS | S r   )r   tuple)xs    r    normalize_tupler   B  s    atHr"   ) KMBTc                     t        dt        t        t              dz
  t        t	        |             dz
  dz              }t        |   S )Nr   r   rA   r   )maxminr   suffixesstr)numberindexs     r    get_suffix_strr   K  s=     3s8}q(3s6{+;a+?A*EFGEE?r"   c                 X    t         j                  |      }| d|z  z  d}|t         |   z   S )Ni  z.3f)r   r   )r   suffixr   r   s       r    convert_num_with_suffixr   R  s2    NN6"E%c*E8E?""r"   c                     |dk(  ry| |z  dS )Nr   0%z.2%rB   )numdenoms     r    convert_to_percent_strr  Y  s    zEk#r"   c                 .     t                fd       }|S )Nc                 B    t        |       \  }} | }t        ||      S r   )r   r   )r(   	flat_argsspecr   r*   s       r    r+   z)_pytreeify_preserve_structure.<locals>.nf_  s'    &t,	4mc4((r"   r   r,   s   ` r    _pytreeify_preserve_structurer  ^  s     
1X) )
 Ir"   c                        e Zd ZdZ	 	 	 	 ddeeej                  j                  e	ej                  j                     f      de
dedeeeef      f fdZde
fdZdeeeee
f   f   fd	Zdd
Zd Zd Zd Z xZS )r   a  
    ``FlopCounterMode`` is a context manager that counts the number of flops within its context.

    It does this using a ``TorchDispatchMode``.

    It also supports hierarchical output by passing a module (or list of
    modules) to FlopCounterMode on construction. If you do not need hierarchical
    output, you do not need to use it with a module.

    Example usage

    .. code-block:: python

        mod = ...
        with FlopCounterMode(mod) as flop_counter:
            mod.sum().backward()

    modsdepthdisplaycustom_mappingc                 d   t         |           t        d       | _        || _        || _        d | _        |i }|t        j                  dd       i t        |j                         D ci c]   \  }}|t        |dd      r|n
t        |      " c}}| _	        t               | _        y c c}}w )Nc                       t        t              S r   )r   intrB   r"   r    <lambda>z*FlopCounterMode.__init__.<locals>.<lambda>  s    +VYJZ r"   z<mods argument is not needed anymore, you can stop passing itrA   )
stacklevel_get_rawF)super__init__r   flop_countsr
  r  modewarningswarnr#   itemsgetattrr-   r   mod_tracker)selfr	  r
  r  r  rF   v	__class__s          r    r  zFlopCounterMode.__init__|  s     	6ABZ6[
04	!NMMXefg

WeWkWkWmntqRSqwq*e4!-:JJn
 )? os   -%B,r.   c                 N    t        | j                  d   j                               S )NGlobal)r   r  valuesr  s    r    get_total_flopszFlopCounterMode.get_total_flops  s!    4##H-44677r"   c                 |    | j                   j                         D ci c]  \  }}|t        |       c}}S c c}}w )a  Return the flop counts as a dictionary of dictionaries.

        The outer
        dictionary is keyed by module name, and the inner dictionary is keyed by
        operation name.

        Returns:
            Dict[str, Dict[Any, int]]: The flop counts as a dictionary.
        )r  r  dict)r  rF   r  s      r    get_flop_countszFlopCounterMode.get_flop_counts  s3     (,'7'7'='='?@tq!47
@@@s   8c                    
 | j                   }|d}dd l}d|_        g d}g } j                         
t	        
      d
 fd}t         j                  j                               D ]?  }|dk(  r	|j                  d      d	z   }||kD  r# |||d	z
        }|j                  |       A d j                  v r s|D ]  }	d
|	d   z   |	d<     |dd      |z   }t        |      dk(  rg dg}|j                  ||d      S )Ni?B r   T)ModuleFLOPz% TotalFc           	         t        
j                  |    j                               }	|k\  z  	d|z  }g }|j                  || z   t	        |      t        |      g       
j                  |    j                         D ]<  \  }}|j                  |dz   t        |      z   t	        |      t        |      g       > |S )N z - )r   r  r!  appendr   r  r  r   )mod_namer
  r   paddingr!  rF   r  global_flopsglobal_suffixis_global_subsumedr  s          r    process_modz.FlopCounterMode.get_table.<locals>.process_mod  s     d..x8??ABK+"==EkGFMM("']C&{LA 
 ((288: 1eOc!f,+A}=*1l;  Mr"   r   .r   r+  )r   0r   )leftrightr6  )headerscolalign)r
  tabulatePRESERVE_WHITESPACEr#  r   sortedr  keyscountextendr   )r  r
  r9  headerr!  r2  mod	mod_depth
cur_valuesr   r/  r0  r1  s   `         @@@r    	get_tablezFlopCounterMode.get_table  s.   =JJE=E'+$.++-&|4"	, $**//12 	&Ch		#*I5 $S)a-8JMM*%	& t'''0B *q>a* !1-6Fv;!+,F  B\ ]]r"   c                     | j                   j                          | j                  j                          t	        |       | _        | j
                  j                          | S r   )r  clearr  	__enter___FlopCounterModer  r"  s    r    rF  zFlopCounterMode.__enter__  sG     ""$$T*			r"   c                     | j                   J  | j                   j                  | }d | _         | j                  j                          | j                  r$t	        | j                  | j                               |S r   )r  __exit__r  r  printrC  r
  )r  r(   rP   s      r    rI  zFlopCounterMode.__exit__  sb    yy$$$DII%	!!#<<$..,-r"   c                     || j                   v rY| j                   |   } ||i |d|i}t        | j                  j                        D ]  }| j                  |   |xx   |z  cc<    |S )Nr%   )r#   setr  parentsr  )r  func_packetr   r(   r)   flop_count_funcrx   pars           r    _count_flopszFlopCounterMode._count_flops  sx    $,,,"00=O($F&F#FJ4++334 A  %k2j@2A 
r"   )NrA   TNr   )__name__
__module____qualname____doc__r	   r
   r   nnr(  rr   r  boolr%  r   r  r#  r   r&  rC  rF  rI  rQ  __classcell__)r  s   @r    r   r   h  s    * MQ 7;+5$uxx2G!GHI+ + 	+
 %T#s(^4+*8 8
Ac4S>&9!: 
A:^zr"   c                   0    e Zd ZdZdefdZd Zd ZddZy)	rG  Tcounterc                     || _         y r   )rZ  )r  rZ  s     r    r  z_FlopCounterMode.__init__  s	    r"   c                     ddl }|j                  | j                  j                        }| 5   || }ddd       |j                  | j                  j                        }|| j                  _        |fS # 1 sw Y   CxY w)a  Execute a branch function and capture its FLOP counts without
        affecting self.counter.flop_counts

        Args:
            branch_fn: The branch function to execute
            operands: Arguments to pass to the branch function

        Returns:
            Tuple of (result, flop_counts) where result is the branch output
            and flop_counts is a copy of the FLOP counts after execution
        r   N)copyrZ  r  )r  	branch_fnoperandsr]  checkpointed_flop_countsresultr  s          r    $_execute_with_isolated_flop_countingz5_FlopCounterMode._execute_with_isolated_flop_counting  sq     	#'99T\\-E-E#F  	*)F	*ii 8 89#; {""		* 	*s   A44A=c                 >   |t         j                  j                  j                  hvrt        S |t         j                  j                  j                  u rI|\  }}}}| j                  ||      \  }	}
|	t        u rt        S | j                  ||      \  }}|t        u rt        S t        |
j                               t        |j                               z  }i }|D ]  }|
|   }||   }i }t        |j                               t        |j                               z  }|D ]5  }|j                  |d      }|j                  |d      }t        ||      ||<   7 |||<    |j                         D ]-  \  }}| j                  j                  |   j                  |       / |	S y r   )r   opshigher_ordercondNotImplementedrb  rL  r<  getr   r  rZ  r  update)r  functypesr(   r)   predtrue_branchfalse_branchr_  true_outtrue_flop_counts	false_outfalse_flop_countsall_mod_keysmerged_flop_counts	outer_keytrue_func_countsfalse_func_countsmerged_func_countsall_func_keysfunc_keytrue_val	false_val
inner_dicts                           r    _handle_higher_order_opsz)_FlopCounterMode._handle_higher_order_ops  s   		..3366!! 599))...8<5D+|X)-)R)RX*&H& >)%%+/+T+Th,(I( N*%% /4467#>O>T>T>V:WWL!#) C	#3I#> $5i$@!%'" #$4$9$9$; <sCTCYCYC[?\ \ - LH/33Ha@H 1 5 5h BI36x3K&x0L
 1C"9-C *<)A)A)C G%	:((3:::FG
 OO /r"   Nc                 B   |r|ni }|t         j                  j                  j                  j                  t         j                  j                  j
                  j                  t         j                  j                  j
                  j                  t         j                  j                  j                  j                  t         j                  j                  j                  j                  t         j                  j                  j                  j                  t         j                  j                  j                  j                  t         j                  j                  j                  j                  t         j                  j                  j                  j                  t         j                  j                  j                  j                  t         j                  j                  j                  j                  t         j                  j                  j                  j                  t         j                  j                  j                   j                  t         j                  j                  j"                  j                  t         j                  j$                  j&                  j                  hv rt(        S t+        |t         j,                  j.                        r| j1                  ||||      S || j2                  j4                  vra|t         j                  j$                  j6                  j                  ur1| 5   |j8                  |i |}|t(        ur|cd d d        S 	 d d d         ||i |}| j2                  j;                  |j<                  |||      S # 1 sw Y   9xY wr   )r   rd  atensym_is_contiguousdefaultis_contiguousmemory_formatis_strides_like_formatis_non_overlapping_and_denser   sym_sizestride
sym_stridestorage_offsetsym_storage_offsetnumel	sym_numeldimprimlayoutrg  r   r3   HigherOrderOperatorr~  rZ  r#   r   	decomposerQ  _overloadpacket)r  rj  rk  r(   r)   rr   s          r    __torch_dispatch__z#_FlopCounterMode.__torch_dispatch__A  sK   !r EIINN44<<IINN0088IINN00>>IINN99AAIINN??GGIINN''//IINN++33IINN))11IINN--55IINN1199IINN55==IINN((00IINN,,44IINN&&..IINN))113 3  "!dEJJ::;00udFKK t||111d%))..BWBWB_B_6_ "DNND3F3N* * D#F#||(()=)=sD&QQ s   6NN)rB   N)	rR  rS  rT  supports_higher_order_operatorsr   r  rb  r~  r  rB   r"   r    rG  rG    s%    &*# #(/b"Rr"   rG  )Fr   )NNNFN)Xr   torch.utils._pytreer   r   r   module_trackerr   typingr   r	   r
   r   r   collections.abcr   typing_extensionsr   collectionsr   torch.utils._python_dispatchr   mathr   	functoolsr   r  __all__r   r   rd  r  r!   r#   r%  __annotations__r-   r   mmr  rI   addmmrN   bmmrS   baddbmmrV   
_scaled_mmr^   rr   rW  rh   convolution_convolutioncudnn_convolution_slow_conv2d_forwardro   convolution_backwardr{   r   '_scaled_dot_product_efficient_attention#_scaled_dot_product_flash_attention#_scaled_dot_product_cudnn_attentionr   r   r   r   r   _flash_attention_forwardr   _efficient_attention_forwardr   r   0_scaled_dot_product_efficient_attention_backward,_scaled_dot_product_flash_attention_backward,_scaled_dot_product_cudnn_attention_backwardr   _flash_attention_backwardr   _efficient_attention_backwardr   r   r   r   r   r  r  r   rG  rB   r"   r    <module>r     s    F F ) : : $ ' # :   5
6T]t_yy~~
 !#tCH~ "XxB?O>PRZ[]_a[aRb>b5c , tww/3 #    tzz"%# % #% txx 
C 
 !
 t||$&C & %& t' % 	% (%( 	$#Y$#Y$ Cy$ 	$
 	$L (($*;*;T=S=SUYUnUnopbf Oux O qO
 t001e e 2eN$ DD@@@@B C EI @WZ @C@	-" +` eE#s(OU38_eCHoxPUVY[^V^P_G``ab+`f -` eE#s(OU38_eCHoxPUVY[^V^P_G``ab-`` t44dC  	 D> t88$G 	 H>6 MMIIIIK L ^b Yps YLY t55tD 	 E@ t994H 	 I@GGWJJ
 	HHh 	LL,	
 	OO_ 	i 	y 	I 	y 	1 	00) 	,,i 	,,i 	99;M 	557I  	557I!" 	!!#@#$ 	%%'H""$B&&(J). $# 
L L\mR( mRr"   