+ &jK#^RIt^RIHt^RIHt^RIHtHt^RIHtH t H t H t ^RI H t ^RIHt!RR ]4t]P!R R 44tR R ltRRltRtRtR#)NCallable) dataclass)AnyProtocol)_C_opsautogradTensor)_pytree)utilsc,a]tRt^ toV3RltRtVtR#) InfoProtocolcN<V^8dQh/S[R,;R&S[R,;R&#N _backward_fn_setup_context_fnr)format __classdict__s"o/Users/jameslopez/projects/CWCArchive/cwc-podcast/.venv/lib/python3.14/site-packages/torch/_library/autograd.py __annotate__InfoProtocol.__annotate__ s#T/!$&N__name__ __module__ __qualname____firstlineno____annotate_func____static_attributes____classdictcell__rs@rrr rrc,a]tRt^toV3RltRtVtR#)InfocN<V^8dQh/S[R,;R&S[R,;R&#rr)rrs"rrInfo.__annotate__s%T/! $&rrNrr$s@rr'r'r%rr'cPV^8dQhR\PR\R\/#)ropinforeturn)r OpOverloadrr)rs"rrrs*[[4??[,[8[rc jaaaaa a RSP RSP RSP 2p\P!SP 4o \ !RR44oV3Rlo V VV3RlpVV3Rlp\V\P3R\V4R\V4/4oSP p\;QJd4R .VPOVPO4F 'gK R M) R M%!R .VPOVPO44'd \S4oVVV 3R lpV#) GeneratedBackwardFor__c,a]tRt^toV3RltRtVtR#)$make_autograd_impl..Metadatac\<V^8dQh/S[P;R&S[S[S[3,;R&#)rkeysetkeyword_only_args)rDispatchKeySetdictstrr)rrs"rr1make_autograd_impl..Metadata.__annotate__s+!!! S>)rrNrr$s@rMetadatar3r%rr;c"<VR,pVRRp\P!4;_uu_4VPpVPpSP!V\P ,.VO5/VBpVuuRRR4# +'giR#;i)N)r_AutoDispatchBelowAutogradr5r6 redispatch_after_autograd_keyset)argsmetadatar5kwargsresultr+s* rforward_no_grad+make_autograd_impl..forward_no_grad"sp8CRy  * * , ,__F//F]]6B,E,E#EWWPVWF - , , ,s AA== B c <VR,pVRRp\P!4;_uu_4VPpVPpSP!V\P ,.VO5/VBpSP 'dS\P!SPW4wrS'dSP WWER7MSP WVR7VuuRRR4# +'giR#;i)r=N)ctxinputskeyword_only_inputsoutput)rIrJrLr>) rr?r5r6r@rArr fill_defaults_schema) rIrBrCr5rDrEhas_kwarg_only_argsr,r+s &* rforward#make_autograd_impl..forward,s8CRy  * * , ,__F//F]]6B,E,E#EWWPVWF%%% %222::tL &**&+**s*O/- , , ,s B)C!! C2 c<SP'd]VPpVPRRVnSP!V.VO5!pW n\V\4'd.VORN5#VR3#\ RS R24h XTni;i)NzTrying to backward through zQ but no autograd formula was registered. Please use register_autograd to add one.r>)rneeds_input_grad isinstancetuple RuntimeError)rIgradsprev_needs_input_gradrEr,r+s&* rbackward$make_autograd_impl..backwardIs     =(+(<(<%'*';';CR'@$**377'<$&%((&&4< )".7 8  (=$s 4A?? BrPrYc3b"TF%p\P!VP4xK' R#5iN)r is_tensorlist_like_typetype).0as& r %make_autograd_impl..ds) 5A %%aff--5s-/TFc<\P!4'd8\P!V!'dSP!.VOS!W4N5!pV#S!.VOS!W4N5!pV#r\)ris_grad_enabled_any_requires_gradapply)r5rBr6rE Generatedr;rFs&*, r autograd_impl)make_autograd_impl..autograd_impllsb    B$9$94$@$@__PdPHV,OPF %PdPHV,OPF r) _namespace_opname _overloadnamer rOrNrr^r Function staticmethodany argumentsreturnssupports_tensorlist) r+r,namerPrYschemarhrgr;rFrOs ff @@@@rmake_autograd_implrus' a |1REUEUDVWD33BJJ?***: "    |G,  X. IZZF s 56##5fnn5 sss 56##5fnn5 ( 2  rc0V^8dQhR\R\/#)rclsr-)r)rs"rrrvsjjSjSjrcaaaaVPoVPoVPo\!RR44oVV3RlpV3RlpVV3RlpWnW nW0nV#)a$Allows a given autograd.Function class to support List[Tensor] inputs/outputs. Regular autograd.Function has a constraint that it only directly supports autograd for Tensors. Applying @supports_tensorlist enables an autograd.Function to support autograd for List[Tensor] inputs and outputs. c4a]tRt^toRtRtV3RltRtVtR#)%supports_tensorlist..MetadataNc<V^8dQh/S[P;R&S[PR,;R&S[R,;R&#)r input_specN output_specresult_is_tuple)r TreeSpecbool)rrs"rr2supports_tensorlist..Metadata.__annotate__s?$$$%%,3+ rr) rrrr r}r~r!r"r#r$s@rr;rzs04 '+ rr;c<VR,pVRRp\VS4'g \R4h\P!\ V4VP 4pS!V.VO5!p\V\ 4VnVP'gV3p\P!V\4wrEWRn \VR4'd \R4hW n \ V4#)r=NzNYI: calling supports_tensorlist autograd.Function.forward directly. You should probably be calling .apply instead. Please file an issue if not. _pt_metadataz@Please don't set ctx._pt_metadata; PyTorch uses it to store infor>)rTNotImplementedErrorr tree_unflattenlistr|rUr~ tree_flattennot_list_of_tensorr}hasattrrVr)rIrBrCrE flat_resultr}r; orig_forwards&* r new_forward(supports_tensorlist..new_forwards8CRy(H--%/  %%d4j(2E2EFc)D)#-fe#< '''YF#*#7#7@R#S * 3 ' 'R $[!!rc\<\VR4'g \R4hVPp\P!\ V4VP 4pVPp\P!\ VPRR4VP4VnS!V.VO5!pW0n\V\4'gV3p\P!V\4wrVWbP8wd\RV RVP R24h\VR.,4# Y0ni;i)rzNYI: calling supports_tensorlist autograd.Function.backward directly. This will automatically get called by PyTorch autograd. Please file an issue if you need this.NzRExpected the return from backward to be of the same structure as the inputs. Got: z (return from backward), z (inputs)r>)rrrr rrr}rSr|rTrUrnot_list_of_optional_tensorrV)rIrWrCrX grad_inputsflat_grad_inputsgrad_inputs_spec orig_backwards&* r new_backward)supports_tensorlist..new_backwards0sN++%9  ##&&tE{H4H4HI!$ 4 4 9#*#9#9S))#2./1D1D$C (4e4K#8 +u--&.K .5-A-A 4. * 22 2''7&88Q&&'y2  %.//%$9 s "AD##D+c<\P!V\R7wrS!V4pS!.VOVN5!pVPf \ R4h\P !\ V4VP4pVP'g^\V\4'g\ R\V4 24h\V4^8wd\ R\V4 24hV^,#V#))is_leafz%metadata.output_spec must not be Nonezresult must be tuple, got z%result tuple must have length 1, got ) r rrr}AssertionErrorrrr~rTrUr^len)rB flat_argsr|rCrEr; orig_applys* r new_apply&supports_tensorlist..new_applys ' 4 4TCU V J'1Y11    ' !HI I''V h6J6JK'''fe,,$'A$v,%PQQ6{a$;CK=I!9  r)rPrYrfr)rwrrrr;rrrs& @@@@rrrrrvs];;LLLMJ,,, "2*0X"KLI Jrc\V\4'dR#\V\4'd5\;QJdRV4F 'gK R# R#!RV44#R#)Fc3L"TFp\V\4'*xK R#5ir\rTr r_ls& rra%not_list_of_tensor..s;dz!V,,,ds"$TrTrUrrotrees&rrrsK$$s;d;ss;s;s;d;;; rc\V\4'dR#\V\4'd5\;QJdRV4F 'gK R# R#!RV44#R#)Fc3b"TF%qRJ;'d\V\4'*xK' R#5ir\rrs& rra.not_list_of_optional_tensor..s'M1D=>>Av)>%>>s//Trrs&rrrsK$$sMMssMsMsMMMM r) dataclassescollections.abcrrtypingrrtorchrr r r torch.utilsr r rr'rurrrrrrrrs`$! ,,'8'  ''' [|jZr