You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

index.html 58 kB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828
  1. <!doctype html>
  2. <html lang="en" class="no-js">
  3. <head>
  4. <meta charset="utf-8">
  5. <meta name="viewport" content="width=device-width,initial-scale=1">
  6. <link rel="prev" href="../LoadAndSaveState/">
  7. <link rel="next" href="../SemanticKernelChat/">
  8. <link rel="icon" href="../../media/icon128.png">
  9. <meta name="generator" content="mkdocs-1.4.3, mkdocs-material-9.1.20">
  10. <title>Quantization - LLamaSharp Documentation</title>
  11. <link rel="stylesheet" href="../../assets/stylesheets/main.eebd395e.min.css">
  12. <link rel="stylesheet" href="../../assets/stylesheets/palette.ecc896b0.min.css">
  13. <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
  14. <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Fira+Sans:300,300i,400,400i,700,700i%7CFira+Mono:400,400i,700,700i&display=fallback">
  15. <style>:root{--md-text-font:"Fira Sans";--md-code-font:"Fira Mono"}</style>
  16. <link rel="stylesheet" href="../../css/extra.css?v=14">
  17. <script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce((e,_)=>(e<<5)-e+_.charCodeAt(0),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
  18. </head>
  19. <body dir="ltr" data-md-color-scheme="default" data-md-color-primary="white" data-md-color-accent="red">
  20. <script>var palette=__md_get("__palette");if(palette&&"object"==typeof palette.color)for(var key of Object.keys(palette.color))document.body.setAttribute("data-md-color-"+key,palette.color[key])</script>
  21. <input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
  22. <input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
  23. <label class="md-overlay" for="__drawer"></label>
  24. <div data-md-component="skip">
  25. <a href="#quantization" class="md-skip">
  26. Skip to content
  27. </a>
  28. </div>
  29. <div data-md-component="announce">
  30. </div>
  31. <div data-md-color-scheme="default" data-md-component="outdated" hidden>
  32. </div>
  33. <header class="md-header md-header--shadow" data-md-component="header">
  34. <nav class="md-header__inner md-grid" aria-label="Header">
  35. <a href="../.." title="LLamaSharp Documentation" class="md-header__button md-logo" aria-label="LLamaSharp Documentation" data-md-component="logo">
  36. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13 9h5.5L13 3.5V9M6 2h8l6 6v12a2 2 0 0 1-2 2H6a2 2 0 0 1-2-2V4c0-1.11.89-2 2-2m9 16v-2H6v2h9m3-4v-2H6v2h12Z"/></svg>
  37. </a>
  38. <label class="md-header__button md-icon" for="__drawer">
  39. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2Z"/></svg>
  40. </label>
  41. <div class="md-header__title" data-md-component="header-title">
  42. <div class="md-header__ellipsis">
  43. <div class="md-header__topic">
  44. <span class="md-ellipsis">
  45. LLamaSharp Documentation
  46. </span>
  47. </div>
  48. <div class="md-header__topic" data-md-component="header-topic">
  49. <span class="md-ellipsis">
  50. Quantization
  51. </span>
  52. </div>
  53. </div>
  54. </div>
  55. <form class="md-header__option" data-md-component="palette">
  56. <input class="md-option" data-md-color-media="(prefers-color-scheme: light)" data-md-color-scheme="default" data-md-color-primary="white" data-md-color-accent="red" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_1">
  57. <label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_2" hidden>
  58. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 7a5 5 0 0 1 5 5 5 5 0 0 1-5 5 5 5 0 0 1-5-5 5 5 0 0 1 5-5m0 2a3 3 0 0 0-3 3 3 3 0 0 0 3 3 3 3 0 0 0 3-3 3 3 0 0 0-3-3m0-7 2.39 3.42C13.65 5.15 12.84 5 12 5c-.84 0-1.65.15-2.39.42L12 2M3.34 7l4.16-.35A7.2 7.2 0 0 0 5.94 8.5c-.44.74-.69 1.5-.83 2.29L3.34 7m.02 10 1.76-3.77a7.131 7.131 0 0 0 2.38 4.14L3.36 17M20.65 7l-1.77 3.79a7.023 7.023 0 0 0-2.38-4.15l4.15.36m-.01 10-4.14.36c.59-.51 1.12-1.14 1.54-1.86.42-.73.69-1.5.83-2.29L20.64 17M12 22l-2.41-3.44c.74.27 1.55.44 2.41.44.82 0 1.63-.17 2.37-.44L12 22Z"/></svg>
  59. </label>
  60. <input class="md-option" data-md-color-media="(prefers-color-scheme: dark)" data-md-color-scheme="slate" data-md-color-primary="blue" data-md-color-accent="blue" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_2">
  61. <label class="md-header__button md-icon" title="Switch to light mode" for="__palette_1" hidden>
  62. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m17.75 4.09-2.53 1.94.91 3.06-2.63-1.81-2.63 1.81.91-3.06-2.53-1.94L12.44 4l1.06-3 1.06 3 3.19.09m3.5 6.91-1.64 1.25.59 1.98-1.7-1.17-1.7 1.17.59-1.98L15.75 11l2.06-.05L18.5 9l.69 1.95 2.06.05m-2.28 4.95c.83-.08 1.72 1.1 1.19 1.85-.32.45-.66.87-1.08 1.27C15.17 23 8.84 23 4.94 19.07c-3.91-3.9-3.91-10.24 0-14.14.4-.4.82-.76 1.27-1.08.75-.53 1.93.36 1.85 1.19-.27 2.86.69 5.83 2.89 8.02a9.96 9.96 0 0 0 8.02 2.89m-1.64 2.02a12.08 12.08 0 0 1-7.8-3.47c-2.17-2.19-3.33-5-3.49-7.82-2.81 3.14-2.7 7.96.31 10.98 3.02 3.01 7.84 3.12 10.98.31Z"/></svg>
  63. </label>
  64. </form>
  65. <label class="md-header__button md-icon" for="__search">
  66. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
  67. </label>
  68. <div class="md-search" data-md-component="search" role="dialog">
  69. <label class="md-search__overlay" for="__search"></label>
  70. <div class="md-search__inner" role="search">
  71. <form class="md-search__form" name="search">
  72. <input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
  73. <label class="md-search__icon md-icon" for="__search">
  74. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
  75. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"/></svg>
  76. </label>
  77. <nav class="md-search__options" aria-label="Search">
  78. <button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
  79. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41Z"/></svg>
  80. </button>
  81. </nav>
  82. </form>
  83. <div class="md-search__output">
  84. <div class="md-search__scrollwrap" data-md-scrollfix>
  85. <div class="md-search-result" data-md-component="search-result">
  86. <div class="md-search-result__meta">
  87. Initializing search
  88. </div>
  89. <ol class="md-search-result__list" role="presentation"></ol>
  90. </div>
  91. </div>
  92. </div>
  93. </div>
  94. </div>
  95. </nav>
  96. </header>
  97. <div class="md-container" data-md-component="container">
  98. <main class="md-main" data-md-component="main">
  99. <div class="md-main__inner md-grid">
  100. <div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
  101. <div class="md-sidebar__scrollwrap">
  102. <div class="md-sidebar__inner">
  103. <nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
  104. <label class="md-nav__title" for="__drawer">
  105. <a href="../.." title="LLamaSharp Documentation" class="md-nav__button md-logo" aria-label="LLamaSharp Documentation" data-md-component="logo">
  106. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13 9h5.5L13 3.5V9M6 2h8l6 6v12a2 2 0 0 1-2 2H6a2 2 0 0 1-2-2V4c0-1.11.89-2 2-2m9 16v-2H6v2h9m3-4v-2H6v2h12Z"/></svg>
  107. </a>
  108. LLamaSharp Documentation
  109. </label>
  110. <ul class="md-nav__list" data-md-scrollfix>
  111. <li class="md-nav__item">
  112. <a href="../.." class="md-nav__link">
  113. Overview
  114. </a>
  115. </li>
  116. <li class="md-nav__item">
  117. <a href="../../QuickStart/" class="md-nav__link">
  118. Quick Start
  119. </a>
  120. </li>
  121. <li class="md-nav__item">
  122. <a href="../../Architecture/" class="md-nav__link">
  123. Architecture
  124. </a>
  125. </li>
  126. <li class="md-nav__item">
  127. <a href="../../FAQ/" class="md-nav__link">
  128. FAQ
  129. </a>
  130. </li>
  131. <li class="md-nav__item">
  132. <a href="../../ContributingGuide/" class="md-nav__link">
  133. Contributing Guide
  134. </a>
  135. </li>
  136. <li class="md-nav__item md-nav__item--nested">
  137. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" >
  138. <label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
  139. Tutorials
  140. <span class="md-nav__icon md-icon"></span>
  141. </label>
  142. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
  143. <label class="md-nav__title" for="__nav_6">
  144. <span class="md-nav__icon md-icon"></span>
  145. Tutorials
  146. </label>
  147. <ul class="md-nav__list" data-md-scrollfix>
  148. <li class="md-nav__item">
  149. <a href="../../Tutorials/NativeLibraryConfig/" class="md-nav__link">
  150. Customize the native library loading
  151. </a>
  152. </li>
  153. <li class="md-nav__item">
  154. <a href="../../Tutorials/Executors/" class="md-nav__link">
  155. Use executors
  156. </a>
  157. </li>
  158. <li class="md-nav__item">
  159. <a href="../../Tutorials/ChatSession/" class="md-nav__link">
  160. Use ChatSession
  161. </a>
  162. </li>
  163. <li class="md-nav__item">
  164. <a href="../../Tutorials/UnderstandLLamaContext/" class="md-nav__link">
  165. Understand LLamaContext
  166. </a>
  167. </li>
  168. <li class="md-nav__item">
  169. <a href="../../Tutorials/GetEmbeddings/" class="md-nav__link">
  170. Get embeddings
  171. </a>
  172. </li>
  173. <li class="md-nav__item">
  174. <a href="../../Tutorials/Quantization/" class="md-nav__link">
  175. Quantize the model
  176. </a>
  177. </li>
  178. </ul>
  179. </nav>
  180. </li>
  181. <li class="md-nav__item md-nav__item--nested">
  182. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" >
  183. <label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
  184. Integrations
  185. <span class="md-nav__icon md-icon"></span>
  186. </label>
  187. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
  188. <label class="md-nav__title" for="__nav_7">
  189. <span class="md-nav__icon md-icon"></span>
  190. Integrations
  191. </label>
  192. <ul class="md-nav__list" data-md-scrollfix>
  193. <li class="md-nav__item">
  194. <a href="../../Integrations/semantic-kernel/" class="md-nav__link">
  195. semantic-kernel integration
  196. </a>
  197. </li>
  198. <li class="md-nav__item">
  199. <a href="../../Integrations/kernel-memory/" class="md-nav__link">
  200. kernel-memory integration
  201. </a>
  202. </li>
  203. <li class="md-nav__item">
  204. <a href="../../Integrations/BotSharp.md" class="md-nav__link">
  205. BotSharp integration
  206. </a>
  207. </li>
  208. <li class="md-nav__item">
  209. <a href="../../Integrations/Langchain.md" class="md-nav__link">
  210. Langchain integration
  211. </a>
  212. </li>
  213. </ul>
  214. </nav>
  215. </li>
  216. <li class="md-nav__item md-nav__item--active md-nav__item--nested">
  217. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8" checked>
  218. <label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="0">
  219. Examples
  220. <span class="md-nav__icon md-icon"></span>
  221. </label>
  222. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="true">
  223. <label class="md-nav__title" for="__nav_8">
  224. <span class="md-nav__icon md-icon"></span>
  225. Examples
  226. </label>
  227. <ul class="md-nav__list" data-md-scrollfix>
  228. <li class="md-nav__item">
  229. <a href="../BatchedExecutorFork/" class="md-nav__link">
  230. Bacthed executor - multi-output to one input
  231. </a>
  232. </li>
  233. <li class="md-nav__item">
  234. <a href="../BatchedExecutorGuidance/" class="md-nav__link">
  235. Batched executor - basic guidance
  236. </a>
  237. </li>
  238. <li class="md-nav__item">
  239. <a href="../BatchedExecutorRewind/" class="md-nav__link">
  240. Batched executor - rewinding to an earlier state
  241. </a>
  242. </li>
  243. <li class="md-nav__item">
  244. <a href="../ChatChineseGB2312/" class="md-nav__link">
  245. Chinese LLM - with GB2312 encoding
  246. </a>
  247. </li>
  248. <li class="md-nav__item">
  249. <a href="../ChatSessionStripRoleName/" class="md-nav__link">
  250. ChatSession - stripping role names
  251. </a>
  252. </li>
  253. <li class="md-nav__item">
  254. <a href="../ChatSessionWithHistory/" class="md-nav__link">
  255. ChatSession - with history
  256. </a>
  257. </li>
  258. <li class="md-nav__item">
  259. <a href="../ChatSessionWithRestart/" class="md-nav__link">
  260. ChatSession - restarting
  261. </a>
  262. </li>
  263. <li class="md-nav__item">
  264. <a href="../ChatSessionWithRoleName/" class="md-nav__link">
  265. ChatSession - Basic
  266. </a>
  267. </li>
  268. <li class="md-nav__item">
  269. <a href="../CodingAssistant/" class="md-nav__link">
  270. Coding assistant
  271. </a>
  272. </li>
  273. <li class="md-nav__item">
  274. <a href="../GetEmbeddings/" class="md-nav__link">
  275. Get embeddings
  276. </a>
  277. </li>
  278. <li class="md-nav__item">
  279. <a href="../GrammarJsonResponse/" class="md-nav__link">
  280. Grammar - json response
  281. </a>
  282. </li>
  283. <li class="md-nav__item">
  284. <a href="../InstructModeExecute/" class="md-nav__link">
  285. Instruct executor - basic
  286. </a>
  287. </li>
  288. <li class="md-nav__item">
  289. <a href="../InteractiveModeExecute/" class="md-nav__link">
  290. Interactive executor - basic
  291. </a>
  292. </li>
  293. <li class="md-nav__item">
  294. <a href="../KernelMemory/" class="md-nav__link">
  295. Kernel memory integration - basic
  296. </a>
  297. </li>
  298. <li class="md-nav__item">
  299. <a href="../KernelMemorySaveAndLoad/" class="md-nav__link">
  300. Kernel-memory - save & load
  301. </a>
  302. </li>
  303. <li class="md-nav__item">
  304. <a href="../LLavaInteractiveModeExecute/" class="md-nav__link">
  305. LLaVA - basic
  306. </a>
  307. </li>
  308. <li class="md-nav__item">
  309. <a href="../LoadAndSaveSession/" class="md-nav__link">
  310. ChatSession - load & save
  311. </a>
  312. </li>
  313. <li class="md-nav__item">
  314. <a href="../LoadAndSaveState/" class="md-nav__link">
  315. Executor - save/load state
  316. </a>
  317. </li>
  318. <li class="md-nav__item md-nav__item--active">
  319. <input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
  320. <a href="./" class="md-nav__link md-nav__link--active">
  321. Quantization
  322. </a>
  323. </li>
  324. <li class="md-nav__item">
  325. <a href="../SemanticKernelChat/" class="md-nav__link">
  326. Semantic-kernel - chat
  327. </a>
  328. </li>
  329. <li class="md-nav__item">
  330. <a href="../SemanticKernelMemory/" class="md-nav__link">
  331. Semantic-kernel - with kernel-memory
  332. </a>
  333. </li>
  334. <li class="md-nav__item">
  335. <a href="../SemanticKernelPrompt/" class="md-nav__link">
  336. Semantic-kernel - basic
  337. </a>
  338. </li>
  339. <li class="md-nav__item">
  340. <a href="../StatelessModeExecute/" class="md-nav__link">
  341. Stateless executor
  342. </a>
  343. </li>
  344. <li class="md-nav__item">
  345. <a href="../TalkToYourself/" class="md-nav__link">
  346. Talk to yourself
  347. </a>
  348. </li>
  349. </ul>
  350. </nav>
  351. </li>
  352. <li class="md-nav__item md-nav__item--nested">
  353. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_9" >
  354. <label class="md-nav__link" for="__nav_9" id="__nav_9_label" tabindex="0">
  355. API Reference
  356. <span class="md-nav__icon md-icon"></span>
  357. </label>
  358. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_9_label" aria-expanded="false">
  359. <label class="md-nav__title" for="__nav_9">
  360. <span class="md-nav__icon md-icon"></span>
  361. API Reference
  362. </label>
  363. <ul class="md-nav__list" data-md-scrollfix>
  364. <li class="md-nav__item">
  365. <a href="../../xmldocs/" class="md-nav__link">
  366. index
  367. </a>
  368. </li>
  369. <li class="md-nav__item">
  370. <a href="../../xmldocs/llama.abstractions.adaptercollection/" class="md-nav__link">
  371. llama.abstractions.adaptercollection
  372. </a>
  373. </li>
  374. <li class="md-nav__item">
  375. <a href="../../xmldocs/llama.abstractions.icontextparams/" class="md-nav__link">
  376. llama.abstractions.icontextparams
  377. </a>
  378. </li>
  379. <li class="md-nav__item">
  380. <a href="../../xmldocs/llama.abstractions.ihistorytransform/" class="md-nav__link">
  381. llama.abstractions.ihistorytransform
  382. </a>
  383. </li>
  384. <li class="md-nav__item">
  385. <a href="../../xmldocs/llama.abstractions.iinferenceparams/" class="md-nav__link">
  386. llama.abstractions.iinferenceparams
  387. </a>
  388. </li>
  389. <li class="md-nav__item">
  390. <a href="../../xmldocs/llama.abstractions.illamaexecutor/" class="md-nav__link">
  391. llama.abstractions.illamaexecutor
  392. </a>
  393. </li>
  394. <li class="md-nav__item">
  395. <a href="../../xmldocs/llama.abstractions.illamaparams/" class="md-nav__link">
  396. llama.abstractions.illamaparams
  397. </a>
  398. </li>
  399. <li class="md-nav__item">
  400. <a href="../../xmldocs/llama.abstractions.imodelparams/" class="md-nav__link">
  401. llama.abstractions.imodelparams
  402. </a>
  403. </li>
  404. <li class="md-nav__item">
  405. <a href="../../xmldocs/llama.abstractions.itextstreamtransform/" class="md-nav__link">
  406. llama.abstractions.itextstreamtransform
  407. </a>
  408. </li>
  409. <li class="md-nav__item">
  410. <a href="../../xmldocs/llama.abstractions.itexttransform/" class="md-nav__link">
  411. llama.abstractions.itexttransform
  412. </a>
  413. </li>
  414. <li class="md-nav__item">
  415. <a href="../../xmldocs/llama.abstractions.loraadapter/" class="md-nav__link">
  416. llama.abstractions.loraadapter
  417. </a>
  418. </li>
  419. <li class="md-nav__item">
  420. <a href="../../xmldocs/llama.abstractions.metadataoverride/" class="md-nav__link">
  421. llama.abstractions.metadataoverride
  422. </a>
  423. </li>
  424. <li class="md-nav__item">
  425. <a href="../../xmldocs/llama.abstractions.metadataoverrideconverter/" class="md-nav__link">
  426. llama.abstractions.metadataoverrideconverter
  427. </a>
  428. </li>
  429. <li class="md-nav__item">
  430. <a href="../../xmldocs/llama.abstractions.tensorsplitscollection/" class="md-nav__link">
  431. llama.abstractions.tensorsplitscollection
  432. </a>
  433. </li>
  434. <li class="md-nav__item">
  435. <a href="../../xmldocs/llama.abstractions.tensorsplitscollectionconverter/" class="md-nav__link">
  436. llama.abstractions.tensorsplitscollectionconverter
  437. </a>
  438. </li>
  439. <li class="md-nav__item">
  440. <a href="../../xmldocs/llama.antipromptprocessor/" class="md-nav__link">
  441. llama.antipromptprocessor
  442. </a>
  443. </li>
  444. <li class="md-nav__item">
  445. <a href="../../xmldocs/llama.batched.alreadypromptedconversationexception/" class="md-nav__link">
  446. llama.batched.alreadypromptedconversationexception
  447. </a>
  448. </li>
  449. <li class="md-nav__item">
  450. <a href="../../xmldocs/llama.batched.batchedexecutor/" class="md-nav__link">
  451. llama.batched.batchedexecutor
  452. </a>
  453. </li>
  454. <li class="md-nav__item">
  455. <a href="../../xmldocs/llama.batched.cannotforkwhilerequiresinferenceexception/" class="md-nav__link">
  456. llama.batched.cannotforkwhilerequiresinferenceexception
  457. </a>
  458. </li>
  459. <li class="md-nav__item">
  460. <a href="../../xmldocs/llama.batched.cannotmodifywhilerequiresinferenceexception/" class="md-nav__link">
  461. llama.batched.cannotmodifywhilerequiresinferenceexception
  462. </a>
  463. </li>
  464. <li class="md-nav__item">
  465. <a href="../../xmldocs/llama.batched.cannotsamplerequiresinferenceexception/" class="md-nav__link">
  466. llama.batched.cannotsamplerequiresinferenceexception
  467. </a>
  468. </li>
  469. <li class="md-nav__item">
  470. <a href="../../xmldocs/llama.batched.cannotsamplerequirespromptexception/" class="md-nav__link">
  471. llama.batched.cannotsamplerequirespromptexception
  472. </a>
  473. </li>
  474. <li class="md-nav__item">
  475. <a href="../../xmldocs/llama.batched.conversation/" class="md-nav__link">
  476. llama.batched.conversation
  477. </a>
  478. </li>
  479. <li class="md-nav__item">
  480. <a href="../../xmldocs/llama.batched.conversationextensions/" class="md-nav__link">
  481. llama.batched.conversationextensions
  482. </a>
  483. </li>
  484. <li class="md-nav__item">
  485. <a href="../../xmldocs/llama.batched.experimentalbatchedexecutorexception/" class="md-nav__link">
  486. llama.batched.experimentalbatchedexecutorexception
  487. </a>
  488. </li>
  489. <li class="md-nav__item">
  490. <a href="../../xmldocs/llama.chatsession-1/" class="md-nav__link">
  491. llama.chatsession-1
  492. </a>
  493. </li>
  494. <li class="md-nav__item">
  495. <a href="../../xmldocs/llama.chatsession/" class="md-nav__link">
  496. llama.chatsession
  497. </a>
  498. </li>
  499. <li class="md-nav__item">
  500. <a href="../../xmldocs/llama.common.authorrole/" class="md-nav__link">
  501. llama.common.authorrole
  502. </a>
  503. </li>
  504. <li class="md-nav__item">
  505. <a href="../../xmldocs/llama.common.chathistory/" class="md-nav__link">
  506. llama.common.chathistory
  507. </a>
  508. </li>
  509. <li class="md-nav__item">
  510. <a href="../../xmldocs/llama.common.fixedsizequeue-1/" class="md-nav__link">
  511. llama.common.fixedsizequeue-1
  512. </a>
  513. </li>
  514. <li class="md-nav__item">
  515. <a href="../../xmldocs/llama.common.inferenceparams/" class="md-nav__link">
  516. llama.common.inferenceparams
  517. </a>
  518. </li>
  519. <li class="md-nav__item">
  520. <a href="../../xmldocs/llama.common.mirostattype/" class="md-nav__link">
  521. llama.common.mirostattype
  522. </a>
  523. </li>
  524. <li class="md-nav__item">
  525. <a href="../../xmldocs/llama.common.modelparams/" class="md-nav__link">
  526. llama.common.modelparams
  527. </a>
  528. </li>
  529. <li class="md-nav__item">
  530. <a href="../../xmldocs/llama.exceptions.grammarexpectedname/" class="md-nav__link">
  531. llama.exceptions.grammarexpectedname
  532. </a>
  533. </li>
  534. <li class="md-nav__item">
  535. <a href="../../xmldocs/llama.exceptions.grammarexpectednext/" class="md-nav__link">
  536. llama.exceptions.grammarexpectednext
  537. </a>
  538. </li>
  539. <li class="md-nav__item">
  540. <a href="../../xmldocs/llama.exceptions.grammarexpectedprevious/" class="md-nav__link">
  541. llama.exceptions.grammarexpectedprevious
  542. </a>
  543. </li>
  544. <li class="md-nav__item">
  545. <a href="../../xmldocs/llama.exceptions.grammarformatexception/" class="md-nav__link">
  546. llama.exceptions.grammarformatexception
  547. </a>
  548. </li>
  549. <li class="md-nav__item">
  550. <a href="../../xmldocs/llama.exceptions.grammarunexpectedcharaltelement/" class="md-nav__link">
  551. llama.exceptions.grammarunexpectedcharaltelement
  552. </a>
  553. </li>
  554. <li class="md-nav__item">
  555. <a href="../../xmldocs/llama.exceptions.grammarunexpectedcharrngelement/" class="md-nav__link">
  556. llama.exceptions.grammarunexpectedcharrngelement
  557. </a>
  558. </li>
  559. <li class="md-nav__item">
  560. <a href="../../xmldocs/llama.exceptions.grammarunexpectedendelement/" class="md-nav__link">
  561. llama.exceptions.grammarunexpectedendelement
  562. </a>
  563. </li>
  564. <li class="md-nav__item">
  565. <a href="../../xmldocs/llama.exceptions.grammarunexpectedendofinput/" class="md-nav__link">
  566. llama.exceptions.grammarunexpectedendofinput
  567. </a>
  568. </li>
  569. <li class="md-nav__item">
  570. <a href="../../xmldocs/llama.exceptions.grammarunexpectedhexcharscount/" class="md-nav__link">
  571. llama.exceptions.grammarunexpectedhexcharscount
  572. </a>
  573. </li>
  574. <li class="md-nav__item">
  575. <a href="../../xmldocs/llama.exceptions.grammarunknownescapecharacter/" class="md-nav__link">
  576. llama.exceptions.grammarunknownescapecharacter
  577. </a>
  578. </li>
  579. <li class="md-nav__item">
  580. <a href="../../xmldocs/llama.exceptions.llamadecodeerror/" class="md-nav__link">
  581. llama.exceptions.llamadecodeerror
  582. </a>
  583. </li>
  584. <li class="md-nav__item">
  585. <a href="../../xmldocs/llama.exceptions.loadweightsfailedexception/" class="md-nav__link">
  586. llama.exceptions.loadweightsfailedexception
  587. </a>
  588. </li>
  589. <li class="md-nav__item">
  590. <a href="../../xmldocs/llama.exceptions.runtimeerror/" class="md-nav__link">
  591. llama.exceptions.runtimeerror
  592. </a>
  593. </li>
  594. <li class="md-nav__item">
  595. <a href="../../xmldocs/llama.extensions.icontextparamsextensions/" class="md-nav__link">
  596. llama.extensions.icontextparamsextensions
  597. </a>
  598. </li>
  599. <li class="md-nav__item">
  600. <a href="../../xmldocs/llama.extensions.imodelparamsextensions/" class="md-nav__link">
  601. llama.extensions.imodelparamsextensions
  602. </a>
  603. </li>
  604. <li class="md-nav__item">
  605. <a href="../../xmldocs/llama.grammars.grammar/" class="md-nav__link">
  606. llama.grammars.grammar
  607. </a>
  608. </li>
  609. <li class="md-nav__item">
  610. <a href="../../xmldocs/llama.grammars.grammarrule/" class="md-nav__link">
  611. llama.grammars.grammarrule
  612. </a>
  613. </li>
  614. <li class="md-nav__item">
  615. <a href="../../xmldocs/llama.ichatmodel/" class="md-nav__link">
  616. llama.ichatmodel
  617. </a>
  618. </li>
  619. <li class="md-nav__item">
  620. <a href="../../xmldocs/llama.llamacache/" class="md-nav__link">
  621. llama.llamacache
  622. </a>
  623. </li>
  624. <li class="md-nav__item">
  625. <a href="../../xmldocs/llama.llamaembedder/" class="md-nav__link">
  626. llama.llamaembedder
  627. </a>
  628. </li>
  629. <li class="md-nav__item">
  630. <a href="../../xmldocs/llama.llamamodel/" class="md-nav__link">
  631. llama.llamamodel
  632. </a>
  633. </li>
  634. <li class="md-nav__item">
  635. <a href="../../xmldocs/llama.llamamodelv1/" class="md-nav__link">
  636. llama.llamamodelv1
  637. </a>
  638. </li>
  639. <li class="md-nav__item">
  640. <a href="../../xmldocs/llama.llamaparams/" class="md-nav__link">
  641. llama.llamaparams
  642. </a>
  643. </li>
  644. <li class="md-nav__item">
  645. <a href="../../xmldocs/llama.llamaquantizer/" class="md-nav__link">
  646. llama.llamaquantizer
  647. </a>
  648. </li>
  649. <li class="md-nav__item">
  650. <a href="../../xmldocs/llama.llamastate/" class="md-nav__link">
  651. llama.llamastate
  652. </a>
  653. </li>
  654. <li class="md-nav__item">
  655. <a href="../../xmldocs/llama.llamatransforms/" class="md-nav__link">
  656. llama.llamatransforms
  657. </a>
  658. </li>
  659. <li class="md-nav__item">
  660. <a href="../../xmldocs/llama.llavaweights/" class="md-nav__link">
  661. llama.llavaweights
  662. </a>
  663. </li>
  664. <li class="md-nav__item">
  665. <a href="../../xmldocs/llama.native.decoderesult/" class="md-nav__link">
  666. llama.native.decoderesult
  667. </a>
  668. </li>
  669. <li class="md-nav__item">
  670. <a href="../../xmldocs/llama.native.ggmltype/" class="md-nav__link">
  671. llama.native.ggmltype
  672. </a>
  673. </li>
  674. <li class="md-nav__item">
  675. <a href="../../xmldocs/llama.native.gpusplitmode/" class="md-nav__link">
  676. llama.native.gpusplitmode
  677. </a>
  678. </li>
  679. <li class="md-nav__item">
  680. <a href="../../xmldocs/llama.native.llamabatch/" class="md-nav__link">
  681. llama.native.llamabatch
  682. </a>
  683. </li>
  684. <li class="md-nav__item">
  685. <a href="../../xmldocs/llama.native.llamabeamsstate/" class="md-nav__link">
  686. llama.native.llamabeamsstate
  687. </a>
  688. </li>
  689. <li class="md-nav__item">
  690. <a href="../../xmldocs/llama.native.llamabeamview/" class="md-nav__link">
  691. llama.native.llamabeamview
  692. </a>
  693. </li>
  694. <li class="md-nav__item">
  695. <a href="../../xmldocs/llama.native.llamachatmessage/" class="md-nav__link">
  696. llama.native.llamachatmessage
  697. </a>
  698. </li>
  699. <li class="md-nav__item">
  700. <a href="../../xmldocs/llama.native.llamacontextparams/" class="md-nav__link">
  701. llama.native.llamacontextparams
  702. </a>
  703. </li>
  704. <li class="md-nav__item">
  705. <a href="../../xmldocs/llama.native.llamaftype/" class="md-nav__link">
  706. llama.native.llamaftype
  707. </a>
  708. </li>
  709. <li class="md-nav__item">
  710. <a href="../../xmldocs/llama.native.llamagrammarelement/" class="md-nav__link">
  711. llama.native.llamagrammarelement
  712. </a>
  713. </li>
  714. <li class="md-nav__item">
  715. <a href="../../xmldocs/llama.native.llamagrammarelementtype/" class="md-nav__link">
  716. llama.native.llamagrammarelementtype
  717. </a>
  718. </li>
  719. <li class="md-nav__item">
  720. <a href="../../xmldocs/llama.native.llamakvcacheview/" class="md-nav__link">
  721. llama.native.llamakvcacheview
  722. </a>
  723. </li>
  724. <li class="md-nav__item">
  725. <a href="../../xmldocs/llama.native.llamakvcacheviewcell/" class="md-nav__link">
  726. llama.native.llamakvcacheviewcell
  727. </a>
  728. </li>
  729. <li class="md-nav__item">
  730. <a href="../../xmldocs/llama.native.llamakvcacheviewsafehandle/" class="md-nav__link">
  731. llama.native.llamakvcacheviewsafehandle
  732. </a>
  733. </li>
  734. <li class="md-nav__item">
  735. <a href="../../xmldocs/llama.native.llamaloglevel/" class="md-nav__link">
  736. llama.native.llamaloglevel
  737. </a>
  738. </li>
  739. <li class="md-nav__item">
  740. <a href="../../xmldocs/llama.native.llamamodelkvoverridetype/" class="md-nav__link">
  741. llama.native.llamamodelkvoverridetype
  742. </a>
  743. </li>
  744. <li class="md-nav__item">
  745. <a href="../../xmldocs/llama.native.llamamodelmetadataoverride/" class="md-nav__link">
  746. llama.native.llamamodelmetadataoverride
  747. </a>
  748. </li>
  749. <li class="md-nav__item">
  750. <a href="../../xmldocs/llama.native.llamamodelparams/" class="md-nav__link">
  751. llama.native.llamamodelparams
  752. </a>
  753. </li>
  754. <li class="md-nav__item">
  755. <a href="../../xmldocs/llama.native.llamamodelquantizeparams/" class="md-nav__link">
  756. llama.native.llamamodelquantizeparams
  757. </a>
  758. </li>
  759. <li class="md-nav__item">
  760. <a href="../../xmldocs/llama.native.llamanativebatch/" class="md-nav__link">
  761. llama.native.llamanativebatch
  762. </a>
  763. </li>
  764. <li class="md-nav__item">
  765. <a href="../../xmldocs/llama.native.llamapoolingtype/" class="md-nav__link">
  766. llama.native.llamapoolingtype
  767. </a>
  768. </li>
  769. <li class="md-nav__item">
  770. <a href="../../xmldocs/llama.native.llamapos/" class="md-nav__link">
  771. llama.native.llamapos
  772. </a>
  773. </li>
  774. <li class="md-nav__item">
  775. <a href="../../xmldocs/llama.native.llamaropetype/" class="md-nav__link">
  776. llama.native.llamaropetype
  777. </a>
  778. </li>
  779. <li class="md-nav__item">
  780. <a href="../../xmldocs/llama.native.llamaseqid/" class="md-nav__link">
  781. llama.native.llamaseqid
  782. </a>
  783. </li>
  784. <li class="md-nav__item">
  785. <a href="../../xmldocs/llama.native.llamatoken/" class="md-nav__link">
  786. llama.native.llamatoken
  787. </a>
  788. </li>
  789. <li class="md-nav__item">
  790. <a href="../../xmldocs/llama.native.llamatokendata/" class="md-nav__link">
  791. llama.native.llamatokendata
  792. </a>
  793. </li>
  794. <li class="md-nav__item">
  795. <a href="../../xmldocs/llama.native.llamatokendataarray/" class="md-nav__link">
  796. llama.native.llamatokendataarray
  797. </a>
  798. </li>
  799. <li class="md-nav__item">
  800. <a href="../../xmldocs/llama.native.llamatokendataarraynative/" class="md-nav__link">
  801. llama.native.llamatokendataarraynative
  802. </a>
  803. </li>
  804. <li class="md-nav__item">
  805. <a href="../../xmldocs/llama.native.llamatokentype/" class="md-nav__link">
  806. llama.native.llamatokentype
  807. </a>
  808. </li>
  809. <li class="md-nav__item">
  810. <a href="../../xmldocs/llama.native.llamavocabtype/" class="md-nav__link">
  811. llama.native.llamavocabtype
  812. </a>
  813. </li>
  814. <li class="md-nav__item">
  815. <a href="../../xmldocs/llama.native.llavaimageembed/" class="md-nav__link">
  816. llama.native.llavaimageembed
  817. </a>
  818. </li>
  819. <li class="md-nav__item">
  820. <a href="../../xmldocs/llama.native.nativeapi/" class="md-nav__link">
  821. llama.native.nativeapi
  822. </a>
  823. </li>
  824. <li class="md-nav__item">
  825. <a href="../../xmldocs/llama.native.nativelibraryconfig/" class="md-nav__link">
  826. llama.native.nativelibraryconfig
  827. </a>
  828. </li>
  829. <li class="md-nav__item">
  830. <a href="../../xmldocs/llama.native.ropescalingtype/" class="md-nav__link">
  831. llama.native.ropescalingtype
  832. </a>
  833. </li>
  834. <li class="md-nav__item">
  835. <a href="../../xmldocs/llama.native.safellamacontexthandle/" class="md-nav__link">
  836. llama.native.safellamacontexthandle
  837. </a>
  838. </li>
  839. <li class="md-nav__item">
  840. <a href="../../xmldocs/llama.native.safellamagrammarhandle/" class="md-nav__link">
  841. llama.native.safellamagrammarhandle
  842. </a>
  843. </li>
  844. <li class="md-nav__item">
  845. <a href="../../xmldocs/llama.native.safellamahandlebase/" class="md-nav__link">
  846. llama.native.safellamahandlebase
  847. </a>
  848. </li>
  849. <li class="md-nav__item">
  850. <a href="../../xmldocs/llama.native.safellamamodelhandle/" class="md-nav__link">
  851. llama.native.safellamamodelhandle
  852. </a>
  853. </li>
  854. <li class="md-nav__item">
  855. <a href="../../xmldocs/llama.native.safellavaimageembedhandle/" class="md-nav__link">
  856. llama.native.safellavaimageembedhandle
  857. </a>
  858. </li>
  859. <li class="md-nav__item">
  860. <a href="../../xmldocs/llama.native.safellavamodelhandle/" class="md-nav__link">
  861. llama.native.safellavamodelhandle
  862. </a>
  863. </li>
  864. <li class="md-nav__item">
  865. <a href="../../xmldocs/llama.quantizer/" class="md-nav__link">
  866. llama.quantizer
  867. </a>
  868. </li>
  869. <li class="md-nav__item">
  870. <a href="../../xmldocs/llama.sampling.basesamplingpipeline/" class="md-nav__link">
  871. llama.sampling.basesamplingpipeline
  872. </a>
  873. </li>
  874. <li class="md-nav__item">
  875. <a href="../../xmldocs/llama.sampling.defaultsamplingpipeline/" class="md-nav__link">
  876. llama.sampling.defaultsamplingpipeline
  877. </a>
  878. </li>
  879. <li class="md-nav__item">
  880. <a href="../../xmldocs/llama.sampling.greedysamplingpipeline/" class="md-nav__link">
  881. llama.sampling.greedysamplingpipeline
  882. </a>
  883. </li>
  884. <li class="md-nav__item">
  885. <a href="../../xmldocs/llama.sampling.isamplingpipeline/" class="md-nav__link">
  886. llama.sampling.isamplingpipeline
  887. </a>
  888. </li>
  889. <li class="md-nav__item">
  890. <a href="../../xmldocs/llama.sampling.isamplingpipelineextensions/" class="md-nav__link">
  891. llama.sampling.isamplingpipelineextensions
  892. </a>
  893. </li>
  894. <li class="md-nav__item">
  895. <a href="../../xmldocs/llama.sampling.mirostate2samplingpipeline/" class="md-nav__link">
  896. llama.sampling.mirostate2samplingpipeline
  897. </a>
  898. </li>
  899. <li class="md-nav__item">
  900. <a href="../../xmldocs/llama.sampling.mirostatesamplingpipeline/" class="md-nav__link">
  901. llama.sampling.mirostatesamplingpipeline
  902. </a>
  903. </li>
  904. <li class="md-nav__item">
  905. <a href="../../xmldocs/llama.sessionstate/" class="md-nav__link">
  906. llama.sessionstate
  907. </a>
  908. </li>
  909. <li class="md-nav__item">
  910. <a href="../../xmldocs/llama.streamingtokendecoder/" class="md-nav__link">
  911. llama.streamingtokendecoder
  912. </a>
  913. </li>
  914. <li class="md-nav__item">
  915. <a href="../../xmldocs/llama.types.chatcompletion/" class="md-nav__link">
  916. llama.types.chatcompletion
  917. </a>
  918. </li>
  919. <li class="md-nav__item">
  920. <a href="../../xmldocs/llama.types.chatcompletionchoice/" class="md-nav__link">
  921. llama.types.chatcompletionchoice
  922. </a>
  923. </li>
  924. <li class="md-nav__item">
  925. <a href="../../xmldocs/llama.types.chatcompletionchunk/" class="md-nav__link">
  926. llama.types.chatcompletionchunk
  927. </a>
  928. </li>
  929. <li class="md-nav__item">
  930. <a href="../../xmldocs/llama.types.chatcompletionchunkchoice/" class="md-nav__link">
  931. llama.types.chatcompletionchunkchoice
  932. </a>
  933. </li>
  934. <li class="md-nav__item">
  935. <a href="../../xmldocs/llama.types.chatcompletionchunkdelta/" class="md-nav__link">
  936. llama.types.chatcompletionchunkdelta
  937. </a>
  938. </li>
  939. <li class="md-nav__item">
  940. <a href="../../xmldocs/llama.types.chatcompletionmessage/" class="md-nav__link">
  941. llama.types.chatcompletionmessage
  942. </a>
  943. </li>
  944. <li class="md-nav__item">
  945. <a href="../../xmldocs/llama.types.chatmessagerecord/" class="md-nav__link">
  946. llama.types.chatmessagerecord
  947. </a>
  948. </li>
  949. <li class="md-nav__item">
  950. <a href="../../xmldocs/llama.types.chatrole/" class="md-nav__link">
  951. llama.types.chatrole
  952. </a>
  953. </li>
  954. <li class="md-nav__item">
  955. <a href="../../xmldocs/llama.types.completion/" class="md-nav__link">
  956. llama.types.completion
  957. </a>
  958. </li>
  959. <li class="md-nav__item">
  960. <a href="../../xmldocs/llama.types.completionchoice/" class="md-nav__link">
  961. llama.types.completionchoice
  962. </a>
  963. </li>
  964. <li class="md-nav__item">
  965. <a href="../../xmldocs/llama.types.completionchunk/" class="md-nav__link">
  966. llama.types.completionchunk
  967. </a>
  968. </li>
  969. <li class="md-nav__item">
  970. <a href="../../xmldocs/llama.types.completionlogprobs/" class="md-nav__link">
  971. llama.types.completionlogprobs
  972. </a>
  973. </li>
  974. <li class="md-nav__item">
  975. <a href="../../xmldocs/llama.types.completionusage/" class="md-nav__link">
  976. llama.types.completionusage
  977. </a>
  978. </li>
  979. <li class="md-nav__item">
  980. <a href="../../xmldocs/llama.types.embedding/" class="md-nav__link">
  981. llama.types.embedding
  982. </a>
  983. </li>
  984. <li class="md-nav__item">
  985. <a href="../../xmldocs/llama.types.embeddingdata/" class="md-nav__link">
  986. llama.types.embeddingdata
  987. </a>
  988. </li>
  989. <li class="md-nav__item">
  990. <a href="../../xmldocs/llama.types.embeddingusage/" class="md-nav__link">
  991. llama.types.embeddingusage
  992. </a>
  993. </li>
  994. <li class="md-nav__item">
  995. <a href="../../xmldocs/logger/" class="md-nav__link">
  996. logger
  997. </a>
  998. </li>
  999. </ul>
  1000. </nav>
  1001. </li>
  1002. </ul>
  1003. </nav>
  1004. </div>
  1005. </div>
  1006. </div>
  1007. <div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
  1008. <div class="md-sidebar__scrollwrap">
  1009. <div class="md-sidebar__inner">
  1010. <nav class="md-nav md-nav--secondary" aria-label="Table of contents">
  1011. </nav>
  1012. </div>
  1013. </div>
  1014. </div>
  1015. <div class="md-content" data-md-component="content">
  1016. <article class="md-content__inner md-typeset">
  1017. <h1 id="quantization">Quantization<a class="headerlink" href="#quantization" title="Permanent link"></a></h1>
  1018. <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"> 1</span>
  1019. <span class="normal"> 2</span>
  1020. <span class="normal"> 3</span>
  1021. <span class="normal"> 4</span>
  1022. <span class="normal"> 5</span>
  1023. <span class="normal"> 6</span>
  1024. <span class="normal"> 7</span>
  1025. <span class="normal"> 8</span>
  1026. <span class="normal"> 9</span>
  1027. <span class="normal">10</span>
  1028. <span class="normal">11</span>
  1029. <span class="normal">12</span>
  1030. <span class="normal">13</span>
  1031. <span class="normal">14</span>
  1032. <span class="normal">15</span>
  1033. <span class="normal">16</span>
  1034. <span class="normal">17</span>
  1035. <span class="normal">18</span>
  1036. <span class="normal">19</span>
  1037. <span class="normal">20</span>
  1038. <span class="normal">21</span>
  1039. <span class="normal">22</span>
  1040. <span class="normal">23</span>
  1041. <span class="normal">24</span>
  1042. <span class="normal">25</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">namespace</span><span class="w"> </span><span class="nn">LLama.Examples.Examples</span>
  1043. <span class="p">{</span>
  1044. <span class="w"> </span><span class="k">public</span><span class="w"> </span><span class="k">class</span><span class="w"> </span><span class="nc">QuantizeModel</span>
  1045. <span class="w"> </span><span class="p">{</span>
  1046. <span class="w"> </span><span class="k">public</span><span class="w"> </span><span class="k">static</span><span class="w"> </span><span class="k">void</span><span class="w"> </span><span class="nf">Run</span><span class="p">()</span>
  1047. <span class="w"> </span><span class="p">{</span>
  1048. <span class="w"> </span><span class="kt">string</span><span class="w"> </span><span class="n">inputPath</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">UserSettings</span><span class="p">.</span><span class="n">GetModelPath</span><span class="p">();</span>
  1049. <span class="w"> </span><span class="n">Console</span><span class="p">.</span><span class="n">Write</span><span class="p">(</span><span class="s">&quot;Please input your output model path: &quot;</span><span class="p">);</span>
  1050. <span class="w"> </span><span class="kt">var</span><span class="w"> </span><span class="n">outputPath</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">Console</span><span class="p">.</span><span class="n">ReadLine</span><span class="p">();</span>
  1051. <span class="w"> </span><span class="n">Console</span><span class="p">.</span><span class="n">Write</span><span class="p">(</span><span class="s">&quot;Please input the quantize type (one of q4_0, q4_1, q5_0, q5_1, q8_0): &quot;</span><span class="p">);</span>
  1052. <span class="w"> </span><span class="kt">var</span><span class="w"> </span><span class="n">quantizeType</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">Console</span><span class="p">.</span><span class="n">ReadLine</span><span class="p">();</span>
  1053. <span class="w"> </span><span class="k">if</span><span class="w"> </span><span class="p">(</span><span class="n">LLamaQuantizer</span><span class="p">.</span><span class="n">Quantize</span><span class="p">(</span><span class="n">inputPath</span><span class="p">,</span><span class="w"> </span><span class="n">outputPath</span><span class="p">,</span><span class="w"> </span><span class="n">quantizeType</span><span class="p">))</span>
  1054. <span class="w"> </span><span class="p">{</span>
  1055. <span class="w"> </span><span class="n">Console</span><span class="p">.</span><span class="n">WriteLine</span><span class="p">(</span><span class="s">&quot;Quantization succeeded!&quot;</span><span class="p">);</span>
  1056. <span class="w"> </span><span class="p">}</span>
  1057. <span class="w"> </span><span class="k">else</span>
  1058. <span class="w"> </span><span class="p">{</span>
  1059. <span class="w"> </span><span class="n">Console</span><span class="p">.</span><span class="n">WriteLine</span><span class="p">(</span><span class="s">&quot;Quantization failed!&quot;</span><span class="p">);</span>
  1060. <span class="w"> </span><span class="p">}</span>
  1061. <span class="w"> </span><span class="p">}</span>
  1062. <span class="w"> </span><span class="p">}</span>
  1063. <span class="p">}</span>
  1064. </code></pre></div></td></tr></table></div>
  1065. </article>
  1066. </div>
  1067. </div>
  1068. </main>
  1069. <footer class="md-footer">
  1070. <div class="md-footer-meta md-typeset">
  1071. <div class="md-footer-meta__inner md-grid">
  1072. <div class="md-copyright">
  1073. Made with
  1074. <a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
  1075. Material for MkDocs
  1076. </a>
  1077. </div>
  1078. </div>
  1079. </div>
  1080. </footer>
  1081. </div>
  1082. <div class="md-dialog" data-md-component="dialog">
  1083. <div class="md-dialog__inner md-typeset"></div>
  1084. </div>
  1085. <script id="__config" type="application/json">{"base": "../..", "features": ["content.action.edit", "navigation.instant"], "search": "../../assets/javascripts/workers/search.74e28a9f.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": {"provider": "mike"}}</script>
  1086. <script src="../../assets/javascripts/bundle.220ee61c.min.js"></script>
  1087. </body>
  1088. </html>

C#/.NET上易用的LLM高性能推理框架,支持LLaMA和LLaVA系列模型。

Contributors (1)