SrSSKJr SSKJr SSKJr SSKJr SSK J r SSK J r SSK J r SSKJr S rS rS rS r\R*\R,"\R.R05"S S\ R2555rg)zCLists compatible accelerator profiles for GKE Inference Quickstart.) exceptions)util)base)commands)profiles_csv_printer)profiles_printer_ga)resource_printerzx To list compatible accelerator profiles for a model, run: $ {command} --model=deepseek-ai/DeepSeek-R1-Distill-Qwen-7B c>[U5n[X- S-5nX4$)z5Converts a decimal representation to an Amount proto.eA)int) decimal_valueunitsnanoss )lib/surface/container/ai/profiles/list.pydecimal_to_amountr"s( m % }$+ ,% cXURnU(dSnXRS- -7nUS$)z*Converts cost to a decimal representation.rr z.3frr)costrr s ramount_to_decimalr+s2 **%  EJJ,,-- # rcSnU(a,USR(a[USR5nSnU(a,USR(a[USR5nX!4$)zjReturns the cost per million normalized output tokens as a decimal. Args: costs: The costs to convert. zN/Ar)costPerMillionOutputTokensrcostPerMillionInputTokens)costsoutput_token_costinput_token_costs rget_decimal_costr4sf  uQx22) a++ uQx11(q)K)KL  ..rc.\rSrSrSr\S5rSrSrg)ListEa List compatible accelerator profiles. This command lists all supported accelerators with their performance details. By default, the supported accelerators are displayed in a table format with select information for each accelerator. To see all details, use --format=yaml or --format=csvprofile. To get supported model, model servers, and model server versions, run `gcloud container ai profiles models list`, `gcloud container ai profiles model-servers list`, and `gcloud container ai profiles model-server-versions list`. czURSSS9 URSSS9 URSSS9 URS[S S 9 URS [S S 9 URS [SSS9 URS[SSS9 URSS[SS9 URSSS9 [R "[ R[ R5 [R "[R[R5 URR[ R5 g)Nz--modelz The model.)helpz--model-serverzThe model server version. Default is latest. Other options include the model server version of a profile, all which returns all versions.z--model-server-versionzPThe model server version. If not specified, this defaults to the latest version.z--target-ntpot-millisecondsaThe target normalized time per output token (NTPOT) in milliseconds. NTPOT is measured as the request_latency / output_tokens. If this field is set, the command will only return accelerators that can meet the target ntpot milliseconds and display their throughput performance at the target latency. Otherwise, the command will return all accelerators and display their highest throughput performance.)typer"z--target-ttft-millisecondsaxThe target time to first token (TTFT) in milliseconds. TTFT is measured as the request_latency / output_tokens. If this field is set, the command will only return profiles that can meet the target ttft milliseconds and display their throughput performance at the target latency. Otherwise, the command will return all profiles and display their highest throughput performance.z'--target-cost-per-million-output-tokensFzfThe target cost per million output tokens to filter profiles by, unit is 1 USD up to 5 decimal places.)r#requiredr"z&--target-cost-per-million-input-tokenszeThe target cost per million input tokens to filter profiles by, unit is 1 USD up to 5 decimal places.z--pricing-modelzsThe pricing model to use to calculate token cost. Currently, this supports on-demand, spot, 3-years-cud, 1-year-cud)r$r#r"z--formatzThe output format. Default is profile, which displays the profile information in a table format, including cost conversions. csvprofile displays the profile information in a CSV format.Options include csvprofile, profile, and yaml. ) add_argumentr floatstrr RegisterFormatterprofiles_printerPROFILES_PRINTER_FORMATProfilePrinterrProfileCSVPrinter display_info AddFormat)parsers rArgs List.ArgsUs~        %  5   $  5   1  5  0  5    A   F&&00''&&44.. !!"2"J"JKrc[R"[RR5n[R "[RR5nUR 5nUR(aURUlUR(aURUl UR(d"UR(dUR(aUR5nUR(a+[UR5upgUR!XgS9UlUR(a+[UR5upgUR!XgS9UlUR(aURUlXTlUR+UR,UR.UR0S9nURcURc UR(bXHlUR4R7U5n U R8(a U R8$/$![:R<a*n [>R@"U [RB5eSn A ff=f)Nr)model modelServermodelServerVersion)"rGetClientInstancer ReleaseTrackGAGetMessagesModulePerformanceRequirementstarget_ntpot_millisecondstargetNtpotMillisecondstarget_ttft_millisecondstargetTtftMilliseconds%target_cost_per_million_output_tokens$target_cost_per_million_input_tokens pricing_modelCostrAmountrr pricingModel targetCostFetchProfilesRequestr3 model_servermodel_server_versionperformanceRequirementsprofilesFetchprofileapitools_exceptions HttpErrorr HttpExceptionHTTP_ERROR_FORMAT) selfargsclientmessagesperformance_requirementsrrrrequestresponseerrors rRunList.Runs  # #D$5$5$8$8 9F%%d&7&7&:&:;H'??A %%  ( (6 $$  ' '5 22  4 4    ]]_d 3 3(  6 6 +3//+:+ '  2 2(  5 5 *2*9* &    ..,0)D-- ''!66.g # : : F % < < H % 0 0 <*B'&&w/h     ( (D  $ $UD,B,B CCDsBH+)H++I)?%I$$I)N) __name__ __module__ __qualname____firstlineno____doc__ staticmethodr0rY__static_attributes__r[rrrrEs& [L[Lz8DrrN)r`apitools.base.pyrrM%googlecloudsdk.api_lib.ai.recommenderrgooglecloudsdk.api_lib.utilgooglecloudsdk.calliopergooglecloudsdk.command_lib.runr'googlecloudsdk.command_lib.run.printersrrr)googlecloudsdk.core.resourcer _EXAMPLESrrrDefaultUniverseOnly ReleaseTracksr7r8rr[rrrmsJ>62(3H[9   /"D%%(()dD8==dD*dDr