hSSKJr SSKrSSKrSSKrSSKrSSKJr SSKJ r SSK r SSK r SSK J r J r Jr SSK Jr SSKJrJrJrJr SSKJr SS KJrJrJr SS KJr SS KJrJ r SS K!J"r" S r#Sr$Sr%Sr&Sr'Sr(Sr)Sr*Sr+Sr,0r-\."\ 5Vs0sH$n\/"\0"\ U5\15(dM\0"\ U5U_M& snr2"SS\5r3"SS\5r4"SS\5r5"SS\5r6\RRn\ Rp"S5\RRr\ Rp"S 5\RRt\ Rp"S!5\RRv\ Rp"S"5\RRx\\RRz\\RR|\ 0r?\RRr\ R"S\ RS#9\ R"S$\ RS#94\RRn\ R"S%\ RS#9\ R"S&\ RS#94\RRv\ R"S\ RS#9\ R"S'\ RS#94\RRt\ R"S(\ RS#9\ R"S)\ RS#94\RR|\ R"S\ S#9\ R"S*\ S#94\RRz\ R"S+\S#9\ R"S,\S#940rE\RRr\ R"S\ RS#9\ R"S-\ RS#94\RRn\ R"S.\ RS#9\ R"S&\ RS#94\RRv\ R"S\ RS#9\ R"S/\ RS#94\RRt\ R"S0\ RS#9\ R"S)\ RS#940rF\RRr\ R"S\ RS#9\ R"S&\ RS#94\RRn\ R"S1\ RS#9\ R"S2\ RS#94\RRv\ R"S\ RS#9\ R"S)\ RS#94\RRt\ R"S3\ RS#9\ R"S4\ RS#94\RR|\ R"S\S#9\ R"S,\S#94\RRz\ R"S5\S#9\ R"S6\S#940rGS7S8.S9jrHScS:jrISdS;jrJS<rKSeSfS=jjrLSeSgS>jjrMScShS?jjrNSiS@jrOSiSAjrPSjSBjrQSkSCjrR"SDSE5rS"SFSG5rT"SHSI5rUSJrVSKrWSLrXSMrYSlSNjrZSOr[SmSPjr\SnSQjr]SoSRjr^SpSSjr_SqSTjr`SrSUjraSqSVjrbSrSWjrcSsSXjrdStSYjreSuSZjrfSvS[jrgSwS\jrhSxS]jriSxS^jrjSyS_jrkSyS`jrlSySajrmSySbjrng!\a SrGNf=f!\a SrSr GNf=f!\a Sr"GNf=fs snf)z) annotationsN)Enum)Path) ModelProto TensorProtoexternal_data_helper)onnx_pb) make_graph make_model make_nodemake_tensor_value_info)ReferenceEvaluator)GraphOptimizationLevelInferenceSessionSessionOptions float8e4m3fn)int4uint4)to_array_extendedz onnx.quantizez0.1.0ai.onnxz com.microsoftQuantizeLinear_QuantizeLinear_InputDequantizeLinear_DequantizeLinear_Output _quantizedlc2\rSrSrSrSrSr\S5rSr g)QuantizationMode@rcUR$Nnameselfs ^/var/www/fran/franai/venv/lib/python3.13/site-packages/onnxruntime/quantization/quant_utils.py__str__QuantizationMode.__str__D yycF[U$![a [5ef=fr")rKeyError ValueError)modes r' from_stringQuantizationMode.from_stringGs) #D) ) ,    N) __name__ __module__ __qualname____firstlineno__ IntegerOps QLinearOpsr( staticmethodr0__static_attributes__r3r+r'rr@s%JJr+rc2\rSrSrSrSrSr\S5rSr g)QuantizedValueTypeOrr cUR$r"r#r%s r'r(QuantizedValueType.__str__Sr*r+cF[U$![a [5ef=fr")r=r-r.)vs r'r0QuantizedValueType.from_stringVs) %a( ( ,  r2r3N) r4r5r6r7Input Initializerr(r:r0r;r3r+r'r=r=Os% EKr+r=cV\rSrSrSrSrSrSrSrSr Sr S r \ S 5r \S 5rS rg ) QuantType^rr cUR$r"r#r%s r'r(QuantType.__str__gr*r+cF[U$![a [5ef=fr")rGr-r.)ts r'r0QuantType.from_stringjs( Q<  ,  r2cU[R:Xa[R$U[R:Xa[R $U[R :Xa[R$U[R:Xa[R$U[R:Xa[R$U[R:Xa[R$U[R:Xa[R$[!SU<S35e)NzUnexpected value qtype=.)rGQInt8rINT8QUInt8UINT8QUInt16UINT16QInt16INT16 QFLOAT8E4M3FN FLOAT8E4M3FNQUInt4UINT4QInt4INT4r.r%s r' tensor_typeQuantType.tensor_typeqs 9?? "## # 9## #$$ $ 9$$ $%% % 9## #$$ $ 9** *++ + 9## #$$ $ 9?? "## #24(!<==r+r3N)r4r5r6r7rUrWr]r[rYrar_r(r:r0propertyrcr;r3r+r'rGrG^sR E FM FG E F >>r+rGc2\rSrSrSrSrSr\S5rSr g) QuantFormatrr cUR$r"r#r%s r'r(QuantFormat.__str__r*r+cF[U$![a [5ef=fr")rgr-r.)formats r'r0QuantFormat.from_strings) v& & ,  r2r3N) r4r5r6r7 QOperatorQDQr(r:r0r;r3r+r'rgrgs%I Cr+rgint8uint8int16uint16dtypeiiiiiiiiirii@rJzero_point_indexcd/n[U5GHup4[R"[U5[R5(a&UR [R "U55 OB[U[R5(aUR U5 O[SUSU35eX0:XdMUSnUR[R:Xd UR[R:XdM[SUR35e [U5S:a [U5$US$)Nzarg z is not an array: r|zzero_point cannot be r r) enumeratenumpy issubdtypetypenumberappendarray isinstancendarray TypeErrorrufloat32float16lentuple)r~argsnew_argsiarBs r' _check_typersH$   DGU\\ 2 2 OOEKKN + 5== ) ) OOA d1#%7s;< <  Aww%--'177emm+C"7y ABB "(ma/5?@Xa[@r+cU[;d SUS35eU[RR[RR[RR [RR 4;Ga/US:wa[SU<S35eUR[R:Xa[RnOHUR[R:Xa[RnO[SURS35e[[![#S/S/[$R&R)SU/S/5S 9[#S /S QS /5/S [+SUS5[+SUS5/[+S US5/55n[-U5n[/UR1SXS.5S5$[Un [3USSS9upUb [5X5OU n Ub [7X5OU n [R8"UR;[R5U- R=5U-5n[R>"XXS9 [/UR;U 55$)NUnexpected data type > requested. Only INT8, UINT8, INT16, and UINT16 are supported.rz2zero_point is expected to be null for float 8 not rTzUnexpected dtype Constant zero_point)valuer)XscalerYqurr)rrF) reduce_range symmetric)out) ONNX_TYPE_TO_NP_TYPE onnx_protorr^FLOAT8E4M3FNUZ FLOAT8E5M2FLOAT8E5M2FNUZNotImplementedErrorrurrFLOATrFLOAT16r.r r r onnxhelper make_tensorr rrrunget_qmin_qmax_for_qTypemaxminasarrayastyperoundclip)qTypearrrrlowhigh onnx_type onnx_modelrefruqminqmaxcliplowcliphigharr_fp32s r'quantize_nparrayrs! ( ( w&de ( ++--))--  ?%(Z[eZhhi&jk k 99 %#))I YY%-- '#++I0 1=> > "Bdkk>U>UVbdikmpqor>s.0LseT  *3 4@*7ItD(UD9:  !,3774s)CDQGHH%U+,URWX $'O#d.&*&63t?D==#**U]]";e"C!J!J!Lz!YZ 8h=8??5122r+c US:dUS:a[SUSU35e[R"U[R"SURS95n[R "U[R"SURS95nUb*[ X[R"XPRS9-5nU(aE[R "[R"U5[R"U55nU*nU7nX#::d SUSU35e[R"X- [RS9n[R"U[RS9[R"U[RS9- n[R"Xx- 5n U S:dS5eU [R"UR5R:aA[R"SURS9n [R"SURS9n X/$U(aZ[R"[R"X#-[R"S [RS9- 5URS9n O8[R"[R"X U - - 5URS9n U RUR5n X/$) aCalculate the scale s and zero point z for the quantization relation r = s(q-z), where r are the original values and q are the corresponding quantized values. r and z are calculated such that every value within [rmin,rmax] has an approximate representation within [qmin,qmax]. In addition, qmin <= z <= qmax is enforced. If the symmetric flag is set to True, the interval [rmin,rmax] is symmetrized to [-absmax, +absmax], where absmax = max(abs(rmin), abs(rmax)). :parameter rmin: minimum value of r :parameter rmax: maximum value of r :parameter qmin: minimum value representable by the target quantization data type :parameter qmax: maximum value representable by the target quantization data type :parameter symmetric: True if the floating-point range should be made symmetric. Defaults to False. :parameter min_real_range: Minimum floating-point range (i.e., rmax - rmin) to enforce. Defaults to None. :return: zero and scale [z, s] rBqmin and qmax must meet requirement: qmin <= 0 <= qmax while qmin:, qmmax:rtzqmin=z > qmax=z scale issue?g@)r.rminimumrrumaximumrrabsfloat64finfotinyrr) rminrmaxrrrmin_real_rangeabsmaxdrdqrrs r'compute_scale_zprs( ax4!8]^b]ccklpkqrss ==u{{1DJJ? @D ==u{{1DJJ? @D!4 nJJ OOPuyy $@ww <55htf55< T[ 6B T /%++d%--2X XB KK E A:$}$: u{{4::&+++ Ctzz2[[$**5      T[EKK5==,QQRZ^ZdZdJU[[u 1D%ETZZXJ TZZ(  r+cSnU[;aU[R:XaSSKJn SSKJn Un[S5Vs/sH oS"U5PM nn[R"UVs/sH?n[R"U5(aM [R"U5(aM=UPMA sn[RS9nO[SUS35eU[U'OU[R:XaSSKJn UnUc[S US 35e[R"[U5n [R"SUS9n [R"X- UR S9n X/$s snfs snf) aZCalculate the scale s for a float8 type (E4M3FN). The function assumes the coefficient distribution and the float 8 distribution are similar to two gaussian laws. :return: zero and scale [z, s] More details in notebook `quantization_fp8.ipynb `_. Nr)float8e4m3_to_float32rrtzQuantization to element_type=z not implemented.zUnexpected element_type rT)FLOAT8_DISTRIBUTIONSrr^onnx.numpy_helperr#onnx.reference.custom_element_typesrrangerrisnanisinfrr.rstdru) element_typerzp_dtyperrr all_valuesfvaluesstd_f8zerors r'compute_scale_zp_float8r:s(H// ;33 3 ? H#H :math:`[0, 2^{b-1}]` and - when data `type == int8`, from `[-m , m]` -> :math:`[-(2^{b-1}-1), 2^{b-1}-1]` where `m = max(abs(rmin), abs(rmax))` and add necessary intermediate nodes to transform quantized weight to full weight using the equation :math:`r = S(q-z)`, where - *r*: real original value - *q*: quantized value - *S*: scale - *z*: zero point rwz+One of the quantized value is NaN data in [z, z], quantized_data in [z].zUnexpected value for qType=rT)rrr^ranyrrrqravelrrrrrVrXr\rZrbr`r.) rrrrrrrrrquantized_datanp_datas r' quantize_datarsO82  J ((()%uI %%ekk288:S@SH I ImmD)G=gkkm_Bw{{}o^&&4&8&8&:%;2n>P>P>R=SSUW .00  *%uI.00 25'; <4;a[3S US 35e[A[CUR-555n[RDRGUXR$US S9nU$[RDRIU5n[R"UUS9RUR$5n[RJRMUU5nU$)a Returns a quantized version of the given ONNX initializer. :param weight: The ONNX initializer to quantize. :param quant_type: The final quantized data type. :param zero_point: The zero-point value to use for quantization. :param scale: The scale value to use for quantization. :param axis: The quantization axis if quantizing per-channel. Defaults to None. :param quant_weight_name: The name of the quantized initializer. If not specified, the quantized name is generated. :return: The quantized ONNX initializer. Nr zThe initializer of shape z! could not be created, expecting z, got z and shape=z raw=rTzQuantized weights for z. must be 8-bit before packing as 4-bit values.T)rawrt)'tensor_proto_to_arrayrrshapelistrtakerrrreshape concatenater$TENSOR_NAME_QUANT_SUFFIXrrr^ data_typedimsextendflattencopytobytesraw_datarrstrrbr`rurprqbytespack_bytes_to_4bitrrtensor_dtype_to_np_dtype numpy_helper from_array)weightrrraxisquant_weight_name weight_data q_weight_data channel_count channel_dimsquantized_channel_data_listr channel_data channel_scalechannel_zero_pointquantized_channel_data q_weight_nameq_weight_initializercheck packed_dataquant_np_dtypes r'quantize_onnx_initializerrs((/K*.M |(5F5F5H%\ #))$/ K--.  &(#}%A&++A4L!HM!+ %5..0-& " ( . .u}}=S/T/\/\]i/j k&))*EL ):%6;;-PhOi@jMT%%222#//1)3&!!((5$1!(5(=(=(?(D(D(F(N(N(P%  (&&:;E{{k///5==?mF[F[F]3]"/ 0A0A/BBc$,,.s34F5==?3B;O:PP[\b\h\h[iS!56t<=Q@(  ((--t/?/?/E/EF F   uzz5;;&? ?!7 Ftuv v.}/D/D/FGH  ${{66}jR]R]_jpt6u  ==jI m>JRRSYS^S^_ #00;;M=Y r+cU[RR:Xa [S5eSnU(a[R U5nO0U(aU[ ;a [ UnO[R U5nU(d[SUS35eUupEUS:dUS:a'[SUSUSURS US US U3 5eU$) z Return qmin and qmax, the minimum and maximum value representable by the given qType :parameter qType: onnx.onnx_pb.TensorProto.UINT8 or onnx.onnx_pb.TensorProto.UINT8 :return: qmin, qmax z;This function is not implemented for float 8 as not needed.Nrrrrrz, dtype=z, reduce_range=z , symmetric=z, qType=) rrr^rONNX_INT_TYPE_REDUCED_RANGEgetONNX_INT_TYPE_SYMMETRIC_RANGEONNX_INT_TYPE_RANGEr.ru)rrrqrangerrs r'rr)s  &&333!"_`` F,007 u ==.u5$((/ 07uvwwJD ax4!86$x |?<.Y" 8E7 4  Mr+c"[XUS9up4XC- $)z Helper function to get the quantization range for a type. parameter qType: quantization type. return: quantization range. r)r)rrrrrs r'get_qrange_for_qTyper"Is ) RJD ;r+c@US:aX-OUnUS:=(a X!:nX24$)z Helper function that tries to return a normalized axis in the range [0, rank - 1]. :parameter axis: The axis to normalize. :parameter rank: The tensor rank (number of dimensions). :return (is_valid, axis_norm) rr3)r rank axis_normis_valids r'normalize_axisr'Ss- $ax TIA~2)"2H  r+c[U5nUS:Xa [5$US-S-n[U5nSnSnXAS- :a+XS-S-S-XS--X5'US- nUS- nXAS- :aM+XA:a XS-X5'U$)a. Copies a source array of 8-bit values into a destination bytearray of packed 4-bit values. Assumes that the source values are already in the appropriate int4 range. :parameter src_8bit: The 8-bit element values to pack. :return A bytearray with every two 8-bit src elements packed into a single byte. rr rIrxrK)r bytearray)src_8bit num_elemsdst_sizedstsrc_idst_is r'rr_sH IA~{A !#H H CEE a-  *S0Q68?S;PQ      a-   _s* Jr+c(\rSrSrSr//S4SjrSrg)QuantizedInitializeri}zB Represents a linearly quantized weight input from ONNX operators Nc pXlX lX0lX@lXPlX`lXplXlXlgr") r$ initializerrminsrmaxs zero_pointsscalesrrr ) r&r$r3r4r5r6r7rrr s r'__init__QuantizedInitializer.__init__s4 &  &  , r+) r rr3r$rr5r4r7r6r4r5r6r7__doc__r8r;r3r+r'r1r1}s r+r1c*\rSrSrSrSSjrSrg)QuantizedValueizA Represents a linearly quantized value (input\output\intializer) Nc pXlX lX0lX@lXPlX`lXplXlXlgr") original_nameq_name scale_namezp_name value_typer  node_type node_qtype scale_type) r&r$new_quantized_namerAzero_point_namequantized_value_typer rDrErFs r'r8QuantizedValue.__init__s2"( $& . "$$r+) r rErDr?r@rArFrCrB)NNNNr:r3r+r'r=r=s%r+r=c\rSrSrSrSrSrg)BiasToQuantizeiz# Represents a bias to be quantized c(XlX lX0lgr" bias_name input_name weight_name)r&rOrPrQs r'r8BiasToQuantize.__init__s"$&r+rNNr:r3r+r'rLrLs 'r+rLcURS:Xa[SURS35eURS:XaURnGO,URS:XaURnGOURS:Xa UR nOURS:Xa UR nOURS:Xa URnOURS :Xa URnOURS :Xa URnO}URS :Xa URnO`URS :Xa URnOCURS :Xa URnO&[SURSURS35eURU0$)z Convert attribute to kwarg format for use with onnx.helper.make_node. :parameter attribute: attribute in AttributeProto format. :return: attribute in {key: value} format. rz attribute z does not have type specified.r rIrJrKrLrMry rz has unsupported type rT) rr.r$rrsrQgfloatsintsstringstensorsgraphs) attributers r'attribute_to_kwargr^s; ~~:inn%55STUU~~  1   1   1   1   1    1  1 !! 1 !! 2   :inn%55KINNK[[\]^^ NNE ""r+c~UVs/sHo"RU:XdMUPM nn[U5S:aUS$S$s snf)z Helper function to find item by name in a list. parameter item_name: name of the item. parameter item_list: list of items. return: item if found. None otherwise. rN)r$r) item_name item_listitemitemss r' find_by_namerds@( Bid99 +ATiE B5zA~58/4/ Cs::cXSn[[U55HnXU:XdM UnM U$)z; Helper function to return index of an item in a node list r|)rr) elem_name elem_listelem_idxrs r'get_elem_indexris2H 3y> " <9 $H# Or+cF[RRSX/U5$)z Helper function to create a Mul node. parameter inputs: list of input names. parameter output: output name. parameter name: name of the node. return: Mul node in NodeProto format. Mul)rrr )inputsoutputr$s r' get_mul_noderns ;; $ ??r+clURRURU-UR-5$)zh Helper function to generate a identifiable filepath by concatenating the given identifier as a suffix. )parentjoinpathstemsuffix)filename identifiers r'generate_identified_filenamerv s+ ?? # #HMMJ$>$P QQr+cRSSKnSSKJn SSKnUR"UR S9 [ S5 [ U5 [ S5 [ U5 URXSS9 URS5 URS5 URS 5 UR5 g) Nr) thresholdz Histogram:zHistogram Edges:T)fillz Tensor valueCountszTensor value V.S. Counts) sysmatplotlib.pyplotpyplotrset_printoptionsmaxsizeprintstairsxlabelylabeltitleshow)hist hist_edgesr{pltrs r' apply_plotrs{# S[[1 , $K  *JJtdJ+JJ~JJxII()HHJr+c n ^^^^^SSKmSSKnSSKmSSKJs Js Jn SSKJs Js Jn SSK J mJ mJ m [R"SU35 "UUUUU4SjSTR5nTR!XS9n[#[$R&R)US5S 5nUR+U5 SSS5 TR-S5nUR/S 5n /n [1UR355Hn X n U R55n [7U R9S U5R;55[7U R9S U5R;55/n[=[?U55nU RAU 5nU RAU5nURCU 5 UREU U5 URGU U5 URIU 5nU RKU5 M URMU [OU 55 U HnU RQU5 M U RS5nURUU 5 URWU U5 URYU 5nU R[U5 U R]5n[#[$R&R)US 5S5nUR+U5 SSS5 [$R^R9SS5S;aURRaUS5nURc5n[eU5H\nURgU5n[R"URi55 [R"URk55 M^ [#[$R&R)US5S 5n[1UR355Hn X n U R55n [7U R9S U5R;55[7U R9S U5R;55/nU S-[=[?U55-nUR+U5 UR+S5 M SSS5 g!,(df  GN=f!,(df  GN=f!,(df  g=f)z6 Helper function to write calibration table to files. rN)CalibrationMethod TensorData TensorsDatazcalibration cache: c*>\rSrSrUUUUU4SjrSrg)*write_calibration_table..MyEncoderi2cj>[UTT45(aUR5$[UTR5(a'UR5[ UR 5SS.$[UT5(a"UR R[ U5S.$TRRX5$)Nz numpy.array)rruCLS)rr) rto_dictrtolistrru __class__r4 JSONEncoderdefault)r&objrrrjsonnps r'r2write_calibration_table..MyEncoder.default3s# K899{{}$#rzz** # s399~m\\#011"}}55CII##++D6 6r+r3N)r4r5r6r7rr;)rrrrrsr' MyEncoderr2s  7 7r+r)clszcalibration.jsonwihighestlowestzcalibration.flatbufferswbQUANTIZATION_DEBUG0)r 1zcalibration.cache  )6r flatbuffersr5onnxruntime.quantization.CalTableFlatBuffers.KeyValue quantizationCalTableFlatBuffersKeyValue5onnxruntime.quantization.CalTableFlatBuffers.TrtTableTrtTable"onnxruntime.quantization.calibraterrrlogginginfordumpsopenospathjoinwriterBuildersortedkeysrfloatrrbrr CreateString KeyValueStartKeyValueAddKeyKeyValueAddValue KeyValueEndrTrtTableStartDictVectorrPrependUOffsetTRelative EndVector TrtTableStartTrtTableAddDict TrtTableEndFinishOutputenvironGetRootAsTrtTable DictLengthrDictKeyValue)calibration_cachedirrrrr json_datafilerbuilderkey_value_listkeyrd_valuesrXrflat_key flat_value key_value main_dict cal_tablebufdict_lenrrrrrrs @@@@@r'write_calibration_tabler"s LLLL]] LL&'8&9:;77D$$7 , ># (,,y$/446 7 (,,x.335 6 CK '',))%0 w'2!!':6((1 i(#0& $$Wc..AB# '' 2$!!#I 7# Wi0$$W-I NN9 .. C bggll3 9:D AT 3 B zz~~*C0H<%%77Q? '')xA!q)I LL ) LL* +! bggll3 34c :d+0023C&+F~~'Hhll9d388:;hll8T2779:F#ICK 00E JJu  JJt 4 ; :g : 9L B A ; :s%"R7R6CR& R R#& R4cUS:HR[R5nUS:gR[R5nUR5nURU- nU(dgU[ U5-[ U5- nUS:dSUSUSU35eUR[R5nXqU-U*U--- nUS:*R5S:XdeU$)ajGiven a discrete distribution (may have not been normalized to 1), smooth it by replacing zeros with eps multiplied by a scaling factor and taking the corresponding amount off the non-zero values. Ref: http://web.engr.illinois.edu/~hanj/cs412/bk3/KL-divergence.pdf https://github.com//apache/incubator-mxnet/blob/master/python/mxnet/contrib/quantization.py rNrzn_zeros=z , n_nonzeros=z, eps1=)rrrsumsizer)pepsis_zeros is_nonzerosn_zeros n_nonzeroseps1rs r'smooth_distributionr~sQu}}-H6//%--0KllnG'!J  w % "3 3D #:Q'- |74&QQ: 88EMM "D(Nte{2 22D AI??  !! ! Kr+c[R"UR5SS9n[SURR 55$)NF)load_external_datac3N# UHn[R"U5v M g7fr")ruses_external_data).0 intializers r' *model_has_external_data..s!mUlz#66zBBUls#%)rloadas_posixrgraphr3) model_pathmodels r'model_has_external_datars9 IIj))+ FE mUZU`U`UlUlm mmr+c[5nUR5Ul[RUl0nS/US'[ UR5U4SS/0UD6ng)z Generate model that applies graph optimization (constant folding, etc.) parameter model_path: path to the original onnx model parameter opt_model_path: path to the optimized onnx model :return: optimized onnx model ConstantSharingdisabled_optimizers providersCPUExecutionProviderN)rroptimized_model_filepathrORT_ENABLE_BASICgraph_optimization_levelr)ropt_model_path sess_optionkwargs_s r'optimize_modelrsb!"K+9+B+B+DK(+A+R+RK( F%6$7F !,,. jH^G_jcijAr+cSS0nUR(a:URH*nURURUR05 M, [R R X5 g)z>Tag the model that it went through quantization pre-processingonnx.quant.pre_processonnxruntime.quantNmetadata_propsupdaterrrrset_model_props)rrprops r'add_pre_process_metadatar sS.0CDN ((D  ! !488TZZ"8 9)KK6r+cUR(a7URH'nURS:XdMURS:XdM' g g)zCCheck the model whether it went through quantization pre-processingrrTFrrr)rr s r'model_has_pre_process_metadatars< ((Dxx33 FY8Y) r+cSS0nUR(a:URH*nURURUR05 M, [R R X5 g)N onnx.inferrr)rrrs r'add_infer_metadatarsS"$78N %%A  ! !155!''"2 3&KK6r+cUR(a7URH'nURS:XdMURS:XdM' g g)NrrTFr )rrs r'model_has_infer_metadatars; %%Auu $4G)G& r+cURVs/sH'oR(aURS:XdM%UPM) nn[U5S:wa [S5eUSRnU$s snf)Nrr z$Failed to find proper ai.onnx domainr) opset_importdomainrr.version)ropsetai_onnx_domain opset_versions r'get_opset_versionrsf).););m);<a?@@"1%--M  ns $A*A*c[U5nUn[USU5nUS:a;U[RR:Xa[ R "SUS35 SnOCUS:Xa[ R "SUS35 O"US:a[ R "SUS35 SnX2:wa*[RRX5n[U5nU$) Nrcz$The original model opset version is z, which does not support quantization to float 8. Please update the model to opset >= 19. Automatically update the model to opset 19. Please verify the quantized model.rze, which does not support node fusions. Please update the model to opset >= 11 for better performance.z, which does not support quantization. Please update the model to opset >= 11. Automatically update the model to opset 11. Please verify the quantized model. ) rgetattrrrr^rwarningversion_converterconvert_version&save_and_reload_model_with_shape_infer)r weight_typertarget_opset_versionweight_quant_types r'update_opset_versionr's%e,M( ]KHr/43C3C3P3PP2=/B1 1 " " 2=/BM M  2=/B1 1 ",&&66uS7u= Lr+c[US5n[RR[ U5[ U55 [R "UR 55n[U5 UR5 U$)Nz -inferred) rvrshape_inferenceinfer_shapes_pathrrrrunlink)rinferred_model_pathrs r'load_model_with_shape_inferr-s`6z;O**3z?C@Ss * **r+cU[-$r")QUANT_INPUT_SUFFIXr<s r'add_quant_input_suffixrAs + ++r+c US-$)N_QuantizeLinear_Outputr3r<s r'add_quant_output_suffixrDs 1 11r+c US-$)N_DequantizeLinearr3r<s r'add_dequant_suffixrG!s , ,,r+c US-$)N_DequantizeLinear_Inputr3r<s r'add_dequant_input_suffixrJ%s 2 22r+cU[-$r")DEQUANT_OUTPUT_SUFFIXr<s r'add_dequant_output_suffixrM)s . ..r+)NN)FN)FNNN)r numpy.ndarrayronnx.TensorProto.DataTyperboolrrPr float | NonerrQrrQreturnz#tuple[numpy.ndarray, numpy.ndarray])rRz2tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray])r onnx.TensorProtorrOrrNrrNr z int | Noner z str | NonerRrS)FF)r intr$rTrRztuple[bool, int])r*rrRr))rtrrurrRr)rT)g-C6?)rr)rrrr)rr)rrrRrP)rrrRrT)rrr$rGrRr)rrrRr)rrrRr)r3rrRrN)r=rrRr)rRr)o __future__rrrrr1enumrpathlibrrrrrrr r onnx.helperr r r r onnx.referencer onnxruntimerrrrr ImportErrorrronnx.reference.op_runr __producer__ __version__ onnx_domain ms_domain QUANT_OP_NAMEr@DEQUANT_OP_NAMErLrMODEL_SIZE_THRESHOLDrrrrrTr9rr=rGrgrVrurXr\rZr^rbr`rrrqrprsrrrrrrrrrrrrrr"r'rr1r=rLr^rdrirnrvrrrrrr rrrrr'r-r#rr>rArDrGrJrM)ks0r'res  #   >>&QQ-PP@ ? 7      ,$2'!47 4Dq4Dq SZ[fhiSjloHp* Q'*4Dq  t   #>#>L $  V!4  %++g"6  %++g"6!!5;;x#8''  %  5;;q #DekkRU]b]h]hFi"j%++d%**"Eu{{SV^c^h^hGi!j!!EKK$F TYafamamHn#o  5;;vU[[#I5;;W\didodoKp"q  5;;q#> BV[@\"]%++b"=u{{1TX?Y!Z   5;;q #DekkRU]b]h]hFi"j%++d%**"Eu{{SV^c^h^hGi!j!!EKK$F TYafamamHn#o  5;;vU[[#I5;;W\didodoKp"q !  5;;q #DekkRU]b]h]hFi"j%++c"DekkRT\a\f\fFg!h!!EKK$F TYafamamHn#o  5;;vU[[#I5;;W\didodoKp"q  5;;q#=u{{1TX?Y"Z%++b"=u{{1TX?Y!Z )+ A 13h<~"R#'"&"&;G ;G);G;G ;G ! ;G  ;G ;G);G~hl:=7:=D$( L L )L L   L  L " L L ^@ <>%%8''"#J0@R$Yx2n k 77!H7+,2-3/_ L D E $rsB\ \(\-\<+\< \\ \*)\*-\98\9