Serve your fine-tuned model on Impala. Bring a LoRA adapter, and we deploy it for you to call through serverless or batch.
Impala serves models fine-tuned with LoRA (low-rank adaptation). You bring the adapter, we deploy it with its base model, and you send requests to it through serverless or batch.
What to send us
Either form works:
A separate adapter, alongside the name of the base model it was trained on.
A merged model, with the adapter weights already folded into the base model.
Contact your Impala account team to share it.
How it’s served
The adapter is loaded with the model when it’s deployed, so every request to that deployment uses it. Switching adapters per request isn’t supported yet.
Sending requests
Send requests exactly as you would. See Chat completions for serverless and Run a batch for batch. To run a batch on an adapter you upload yourself, see LoRA adapters in batch.If you retrain full weights often, Impala Leap swaps new checkpoints onto a running deployment without a redeploy.
{"docsConfig":{"theme":"mint","$schema":"https://mintlify.com/docs.json","name":"Impala AI Documentation","colors":{"primary":"#2563eb","light":"#7aa7f5","dark":"#1d4ed8"},"logo":{"light":"https://mintcdn.com/impalaai/56GIWcAxVIuqqB4N/LOGO.png?fit=max\u0026auto=format\u0026n=56GIWcAxVIuqqB4N\u0026q=85\u0026s=bfa04414e9e206d4d746cb5c14c65b64","dark":"https://mintcdn.com/impalaai/iKjilE4KzmFvYW-p/LOGO-LIGHT.png?fit=max\u0026auto=format\u0026n=iKjilE4KzmFvYW-p\u0026q=85\u0026s=89996dfd863a19b2b7f3e1a23d3cd900"},"favicon":"https://mintcdn.com/impalaai/CT_7X33viTgR4c3n/favicon-flipped.png?fit=max\u0026auto=format\u0026n=CT_7X33viTgR4c3n\u0026q=85\u0026s=3274696fdf43018c47e87fe4465d6453","background":{"decoration":"gradient"},"navbar":{"links":[{"href":"/changelog","label":"Product updates"},{"href":"https://www.getimpala.ai/blog","label":"Blog"},{"href":"mailto:orel@getimpala.ai","label":"Support"}]},"footer":{"socials":{"linkedin":"https://www.linkedin.com/company/impala-ai","website":"https://www.getimpala.ai/"}},"fonts":{"family":"rethink sans"},"contextual":{"options":["copy","view","chatgpt","claude","perplexity","mcp","cursor","vscode"],"display":"header"},"styling":{"latex":false},"navigation":{"pages":[]}},"deployment":{"deploymentMetadataValue":{"subdomain":"impalaai","hasAudioNarration":false,"actualSubdomain":"impalaai","customDomains":["docs.getimpala.ai"],"gitSource":{"type":"github","owner":"orel-impala","repo":"docs","deployBranch":"main","contentDirectory":"","isPrivate":false,"mountPath":"","label":""},"entitlements":{"AI_CHAT":{"status":"ENABLED"},"WEB_MCP":{"status":"ENABLED"},"NARRATION":{"status":"ENABLED"}},"buildId":"6af9ac18dc65debd1bc21b1b","clientVersion":"0.0.4270","searchFilterCounts":[{"language":"default","tag":"API reference","count":11},{"language":"default","tag":"Files","count":5},{"language":"default","tag":"Introduction","count":4},{"language":"default","tag":"Serverless inference","count":4},{"language":"default","tag":"Batch inference","count":4},{"language":"default","tag":"Batches","count":4},{"language":"default","tag":"Bring your own cloud (BYOC)","count":3},{"language":"default","tag":"Reference","count":3},{"language":"default","tag":"Bring your own model","count":3},{"language":"default","tag":"Integrations","count":2}]},"assistantConfig":{"enableAskAiButton":false,"enableStarterQuestions":false,"enableContextualStarterQuestions":false,"enableAskAiSearchBar":true},"basePath":"","hasChatPermissions":true,"hasWebMcpPermissions":true,"toggles":[{"name":"kill-isr","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-rbac-roles","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-mintlify-slack","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-integrations-settings","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"rbac-expansion","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-pr-grouping","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-prefix","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"analytics-v7","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"user-flows-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"no-publish-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-onboarding","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving-live","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"stripTemperatureMiddleware","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"support-platform-pylon-zendesk","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"instant-rollback","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications-server","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-fable","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fixed-ai-action-pricing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"site-roles","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automation-resolve-merge-conflict","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"scoped-publishing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"mintql","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"page-level-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-version-history-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"billing-page-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"full-page-search","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workspace-projects","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"assistant-v5","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fork-pr-previews","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"revalidation-jwt","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-sso-scim","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"hobby-abuse-scan","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"dashboard-inbox","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-signup","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-dual-write","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-enabled","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"approve-review-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-metadata","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"sso-setup-deadline-banner","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-serve","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"live-agents","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"starter-pricing","enabled":true,"variant":{"name":"treatment","enabled":true,"payload":{"type":"string","value":"treatment"},"feature_enabled":true},"impressionData":false},{"name":"llms-txt-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"wildcard-email-auth","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false}],"googleFontsInlined":false},"customCss":[]}
{"page":{"pagePath":"lora-adapters","slug":"/lora-adapters","pageMetadata":{"title":"LoRA adapters","description":"Serve your fine-tuned model on Impala. Bring a LoRA adapter, and we deploy it for you to call through serverless or batch.","href":"/lora-adapters"},"description":{"compiledSource":"\"use strict\";\nconst {jsx: _jsx} = arguments[0];\nconst {useMDXComponents: _provideComponents} = arguments[0];\nfunction _createMdxContent(props) {\n const _components = {\n p: \"p\",\n ..._provideComponents(),\n ...props.components\n };\n return _jsx(_components.p, {\n children: \"Serve your fine-tuned model on Impala. Bring a LoRA adapter, and we deploy it for you to call through serverless or batch.\"\n });\n}\nfunction MDXContent(props = {}) {\n const {wrapper: MDXLayout} = {\n ..._provideComponents(),\n ...props.components\n };\n return MDXLayout ? _jsx(MDXLayout, {\n ...props,\n children: _jsx(_createMdxContent, {\n ...props\n })\n }) : _createMdxContent(props);\n}\nreturn {\n default: MDXContent\n};\n","frontmatter":{},"scope":{}},"pageType":"default","mdx":{"mdxSource":{"compiledSource":"\"use strict\";const{Fragment:_Fragment,jsx:_jsx,jsxs:_jsxs}=arguments[0];const{useMDXComponents:_provideComponents}=arguments[0];function _createMdxContent(props){const _components={a:`a`,li:`li`,p:`p`,strong:`strong`,ul:`ul`,..._provideComponents(),...props.components},{Heading}=_components;if(!Heading)_missingMdxReference(`Heading`,true);return _jsxs(_Fragment,{children:[_jsxs(_components.p,{children:[`Impala serves models fine-tuned with `,_jsx(_components.strong,{children:`LoRA`}),` (low-rank adaptation). You bring the adapter, we deploy it with its base model, and you send requests to it through serverless or batch.`]}),`\n`,_jsx(Heading,{level:`2`,id:`what-to-send-us`,children:`What to send us`}),`\n`,_jsx(_components.p,{children:`Either form works:`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`A separate adapter`}),`, alongside the name of the base model it was trained on.`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`A merged model`}),`, with the adapter weights already folded into the base model.`]}),`\n`]}),`\n`,_jsx(_components.p,{children:`Contact your Impala account team to share it.`}),`\n`,_jsx(Heading,{level:`2`,id:`how-it’s-served`,children:`How it’s served`}),`\n`,_jsx(_components.p,{children:`The adapter is loaded with the model when it’s deployed, so every request to that deployment uses it. Switching adapters per request isn’t supported yet.`}),`\n`,_jsx(Heading,{level:`2`,id:`sending-requests`,children:`Sending requests`}),`\n`,_jsxs(_components.p,{children:[`Send requests exactly as you would. See `,_jsx(_components.a,{href:`/send-a-request`,children:`Chat completions`}),` for serverless and `,_jsx(_components.a,{href:`/run-your-first-batch`,children:`Run a batch`}),` for batch. To run a batch on an adapter you upload yourself, see `,_jsx(_components.a,{href:`/lora-batch`,children:`LoRA adapters in batch`}),`.`]}),`\n`,_jsxs(_components.p,{children:[`If you retrain full weights often, `,_jsx(_components.a,{href:`/weight-sync`,children:`Impala Leap`}),` swaps new checkpoints onto a running deployment without a redeploy.`]})]})}function MDXContent(props={}){const{wrapper:MDXLayout}={..._provideComponents(),...props.components};return MDXLayout?_jsx(MDXLayout,{...props,children:_jsx(_createMdxContent,{...props})}):_createMdxContent(props)}return{default:MDXContent};function _missingMdxReference(id,component){throw new Error(`Expected `+(component?`component`:`object`)+\" `\"+id+\"` to be defined: you likely forgot to import, pass, or provide it.\")}","frontmatter":{},"scope":{"config":{},"pageMetadata":{"title":"LoRA adapters","description":"Serve your fine-tuned model on Impala. Bring a LoRA adapter, and we deploy it for you to call through serverless or batch.","href":"/lora-adapters"}}},"mdxSourceWithNoJs":null},"mdxExtracts":{"tableOfContents":[{"title":"What to send us","slug":"what-to-send-us","depth":2,"children":[]},{"title":"How it’s served","slug":"how-it’s-served","depth":2,"children":[]},{"title":"Sending requests","slug":"sending-requests","depth":2,"children":[]}],"codeExamples":{}},"jsLinks":[],"subdomain":"impalaai","siteName":"Impala AI Documentation","title":"LoRA adapters - Impala AI Documentation","navMaps":{"firstHrefInVersion":{},"firstHrefInLanguage":{}},"lastModified":"2026-10-28T13:24:03.717Z","originalFileLocation":"lora-adapters.mdx"},"headHtml":"\u003cscript data-mint-head>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem(\"isDarkMode\")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'\u0026\u0026p!=='dark'\u0026\u0026p!=='system')p=\"system\"}var r=p==='system'?(matchMedia(\"(prefers-color-scheme: dark)\").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute(\"data-theme-preference\",p)})();\u003c/script>\u003cmeta data-mint-head name=\"description\" content=\"Serve your fine-tuned model on Impala. Bring a LoRA adapter, and we deploy it for you to call through serverless or batch.\">\u003cmeta data-mint-head name=\"application-name\" content=\"Impala AI Documentation\">\u003cmeta data-mint-head name=\"generator\" content=\"Mintlify\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/impalaai/U-hxjL9MrmCEu7hF/_generated/favicon/android-chrome-192x192.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"apple-touch-icon\" type=\"image/png\" sizes=\"180x180\" href=\"/mintlify-assets/_mintlify/favicons/impalaai/U-hxjL9MrmCEu7hF/_generated/favicon/apple-touch-icon.png\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/impalaai/U-hxjL9MrmCEu7hF/_generated/favicon/favicon-16x16.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/impalaai/U-hxjL9MrmCEu7hF/_generated/favicon/favicon-32x32.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/impalaai/U-hxjL9MrmCEu7hF/_generated/favicon/favicon.ico\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/impalaai/U-hxjL9MrmCEu7hF/_generated/favicon-dark/android-chrome-192x192.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/impalaai/U-hxjL9MrmCEu7hF/_generated/favicon-dark/favicon-16x16.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/impalaai/U-hxjL9MrmCEu7hF/_generated/favicon-dark/favicon-32x32.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/impalaai/U-hxjL9MrmCEu7hF/_generated/favicon-dark/favicon.ico\" media=\"(prefers-color-scheme: dark)\">\u003cmeta data-mint-head property=\"og:title\" content=\"LoRA adapters - Impala AI Documentation\">\u003cmeta data-mint-head property=\"og:description\" content=\"Serve your fine-tuned model on Impala. Bring a LoRA adapter, and we deploy it for you to call through serverless or batch.\">\u003cmeta data-mint-head property=\"og:site_name\" content=\"Impala AI Documentation\">\u003cmeta data-mint-head property=\"og:url\" content=\"https://docs.getimpala.ai/lora-adapters\">\u003cmeta data-mint-head property=\"og:type\" content=\"website\">\u003cmeta data-mint-head property=\"og:image\" content=\"https://impalaai.mintlify.site/_mintlify/api/og/v2?division=Bring+your+own+model\u0026amp;title=LoRA+adapters\u0026amp;description=Serve+your+fine-tuned+model+on+Impala.+Bring+a+LoRA+adapter%2C+and+we+deploy+it+for+you+to+call+through+serverless+or+batch.\u0026amp;theme=6b61ed0062b27ba13c4e93e6\u0026amp;signature=5c3943767e5d12a5ba7c7c8f0d29a1e54da05ed1d9077b19060d0d1b61712ec0\">\u003cmeta data-mint-head property=\"og:image:width\" content=\"1200\">\u003cmeta data-mint-head property=\"og:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"twitter:card\" content=\"summary_large_image\">\u003cmeta data-mint-head name=\"twitter:title\" content=\"LoRA adapters - Impala AI Documentation\">\u003cmeta data-mint-head name=\"twitter:description\" content=\"Serve your fine-tuned model on Impala. Bring a LoRA adapter, and we deploy it for you to call through serverless or batch.\">\u003cmeta data-mint-head name=\"twitter:image\" content=\"https://impalaai.mintlify.site/_mintlify/api/og/v2?division=Bring+your+own+model\u0026amp;title=LoRA+adapters\u0026amp;description=Serve+your+fine-tuned+model+on+Impala.+Bring+a+LoRA+adapter%2C+and+we+deploy+it+for+you+to+call+through+serverless+or+batch.\u0026amp;theme=6b61ed0062b27ba13c4e93e6\u0026amp;signature=5c3943767e5d12a5ba7c7c8f0d29a1e54da05ed1d9077b19060d0d1b61712ec0\">\u003cmeta data-mint-head name=\"twitter:image:width\" content=\"1200\">\u003cmeta data-mint-head name=\"twitter:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"msapplication-config\" content=\"/mintlify-assets/_mintlify/favicons/impalaai/U-hxjL9MrmCEu7hF/_generated/favicon/browserconfig.xml\">\u003cmeta data-mint-head name=\"apple-mobile-web-app-title\" content=\"Impala AI Documentation\">\u003cmeta data-mint-head name=\"msapplication-TileColor\" content=\"#2563eb\">\u003clink data-mint-head rel=\"canonical\" href=\"https://docs.getimpala.ai/lora-adapters\">\u003clink data-mint-head rel=\"alternate\" type=\"application/xml\" href=\"/sitemap.xml\">\u003clink data-mint-head rel=\"alternate\" type=\"text/markdown\" href=\"/lora-adapters.md\">\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https://docs.getimpala.ai/#organization\",\"name\":\"Impala AI Documentation\",\"url\":\"https://docs.getimpala.ai\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https://mintcdn.com/impalaai/56GIWcAxVIuqqB4N/LOGO.png?fit=max\u0026auto=format\u0026n=56GIWcAxVIuqqB4N\u0026q=85\u0026s=bfa04414e9e206d4d746cb5c14c65b64\"}},{\"@type\":\"WebSite\",\"@id\":\"https://docs.getimpala.ai#website\",\"name\":\"Impala AI Documentation\",\"url\":\"https://docs.getimpala.ai\",\"publisher\":{\"@id\":\"https://docs.getimpala.ai/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https://docs.getimpala.ai/lora-adapters#webpage\",\"url\":\"https://docs.getimpala.ai/lora-adapters\",\"name\":\"LoRA adapters\",\"description\":\"Serve your fine-tuned model on Impala. Bring a LoRA adapter, and we deploy it for you to call through serverless or batch.\",\"dateModified\":\"2026-10-28T13:24:03.717Z\",\"isPartOf\":{\"@id\":\"https://docs.getimpala.ai#website\"},\"breadcrumb\":{\"@id\":\"https://docs.getimpala.ai/lora-adapters#breadcrumb\"}},{\"@type\":\"BreadcrumbList\",\"@id\":\"https://docs.getimpala.ai/lora-adapters#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Impala AI Documentation\",\"item\":\"https://docs.getimpala.ai\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"LoRA adapters\",\"item\":\"https://docs.getimpala.ai/lora-adapters\"}]},{\"@type\":[\"Article\",\"TechArticle\"],\"@id\":\"https://docs.getimpala.ai/lora-adapters#article\",\"headline\":\"LoRA adapters\",\"name\":\"LoRA adapters\",\"description\":\"Serve your fine-tuned model on Impala. Bring a LoRA adapter, and we deploy it for you to call through serverless or batch.\",\"url\":\"https://docs.getimpala.ai/lora-adapters\",\"mainEntityOfPage\":{\"@id\":\"https://docs.getimpala.ai/lora-adapters#webpage\"},\"dateModified\":\"2026-10-28T13:24:03.717Z\",\"publisher\":{\"@id\":\"https://docs.getimpala.ai/#organization\"},\"isPartOf\":{\"@id\":\"https://docs.getimpala.ai#website\"}}]}\u003c/script>\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"name\":\"Impala AI Documentation\",\"publisher\":{\"@type\":\"Organization\",\"name\":\"Impala AI Documentation\"},\"provider\":{\"@type\":\"Organization\",\"name\":\"Mintlify\",\"url\":\"https://mintlify.com\"}}\u003c/script>","agentPointerHref":"/lora-adapters.md","siteName":"Impala AI Documentation","nav":{"global":null,"groups":[{"group":"Introduction","icon":"compass","pages":[{"title":"Introduction","href":"/introduction"},{"title":"Run async and open source","href":"/async-inference"},{"title":"Completion windows","href":"/completion-windows"},{"title":"Run in our cloud, or yours","href":"/deployment-options"}]},{"group":"Serverless inference","icon":"bolt","pages":[{"title":"Quickstart","href":"/impala-cloud-setup"},{"title":"Chat completions","href":"/send-a-request"},{"title":"Rate limit webhooks","href":"/rate-limit-webhooks"},{"title":"Billing API","href":"/billing-api"}]},{"group":"Batch inference","icon":"layer-group","pages":[{"title":"Run a batch","href":"/run-your-first-batch"},{"title":"Jobs","href":"/jobs-and-job-ids"},{"title":"Images","href":"/pass_images_with_image_url"},{"title":"Video","href":"/video-input"}]},{"group":"Agent orchestration","icon":"sitemap","pages":[{"title":"Impala Swarm","href":"/swarm"}]},{"group":"Optimization","icon":"gauge","pages":[{"title":"Impala Herd","description":"Herd is the inference engine every Impala workload runs on. It reads the shape of your live traffic and reconfigures itself around it — kernels, batching, decoding.","href":"/impala-herd"}]},{"group":"Bring your own model","icon":"cube","pages":[{"title":"LoRA adapters","href":"/lora-adapters"},{"title":"LoRA adapters in batch","description":"Run a batch on your own fine-tune. Put the adapter in your data plane's resources bucket and name it in the model field.","href":"/lora-batch"},{"title":"Impala Leap","href":"/weight-sync"}]},{"group":"Bring your own cloud (BYOC)","icon":"cloud","pages":[{"title":"Install Impala in your VPC","href":"/getting-started-infrastructure-setup"},{"title":"Expose the OpenAI API endpoint","href":"/exposing_the_openai_api_endpoint_service"},{"title":"Raise AWS service quotas","href":"/aws_service_quotas_for_Impala_data_plane_deployment"}]},{"group":"Integrations","icon":"plug","pages":[{"title":"LiteLLM","href":"/connect-litellm"},{"title":"Anthropic SDKs and Claude Code","href":"/anthropic-sdk"}]},{"group":"Reference","icon":"book","pages":[{"title":"Security \u0026 data handling","href":"/security"},{"title":"Further reading","href":"/further-reading"},{"title":"Glossary","href":"/glossary"}]},{"group":"API reference","icon":"code","pages":[{"group":"System","pages":[{"title":"Health","deprecated":null,"version":null,"openapi":"/openai-api-swagger.json get /health","href":"/api-reference/system/health"},{"title":"Ready","deprecated":null,"version":null,"openapi":"/openai-api-swagger.json get /ready","href":"/api-reference/system/ready"}]},{"group":"Files","pages":[{"title":"List Files","deprecated":null,"version":null,"openapi":"/openai-api-swagger.json get /v1/files","href":"/api-reference/files/list-files"},{"title":"Upload File","deprecated":null,"version":null,"openapi":"/openai-api-swagger.json post /v1/files","href":"/api-reference/files/upload-file"},{"title":"Get File","deprecated":null,"version":null,"openapi":"/openai-api-swagger.json get /v1/files/{file_id}","href":"/api-reference/files/get-file"},{"title":"Delete File","deprecated":null,"version":null,"openapi":"/openai-api-swagger.json delete /v1/files/{file_id}","href":"/api-reference/files/delete-file"},{"title":"Get File Content","deprecated":null,"version":null,"openapi":"/openai-api-swagger.json get /v1/files/{file_id}/content","href":"/api-reference/files/get-file-content"}]},{"group":"Batches","pages":[{"title":"List Batches","deprecated":null,"version":null,"openapi":"/openai-api-swagger.json get /v1/batches","href":"/api-reference/batches/list-batches"},{"title":"Create Batch","deprecated":null,"version":null,"openapi":"/openai-api-swagger.json post /v1/batches","href":"/api-reference/batches/create-batch"},{"title":"Get Batch","deprecated":null,"version":null,"openapi":"/openai-api-swagger.json get /v1/batches/{batch_id}","href":"/api-reference/batches/get-batch"},{"title":"Cancel Batch","deprecated":null,"version":null,"openapi":"/openai-api-swagger.json post /v1/batches/{batch_id}/cancel","href":"/api-reference/batches/cancel-batch"}]}]}]},"basePath":"","title":"LoRA adapters - Impala AI Documentation","deploymentId":"dpl_DyXGnKeCjZyA3sUdfMJ7FjkdBefg","buildId":"dpl_DyXGnKeCjZyA3sUdfMJ7FjkdBefg","dynamics":[],"chunks":[]}