{"nav":{"global":null,"tabs":[{"tab":"Documentation","groups":[{"group":"Get Started","pages":[{"title":"Serverless GPU inference on AWS with Tensorfuse","sidebarTitle":"Introduction","mode":"wide","href":"/concepts/introduction"},{"title":"Getting Started","href":"/concepts/getting_started_tensorkube"}]},{"group":"LLM Inference","pages":[{"title":"Run serverless LLM inference on AWS","sidebarTitle":"Inference on AWS","href":"/guides/inference/overview"},{"title":"Choose an open model for self-hosted inference","sidebarTitle":"Choose an open model","href":"/guides/inference/open-models"},{"title":"vLLM vs SGLang: choose an LLM inference engine","sidebarTitle":"vLLM vs SGLang","href":"/guides/inference/vllm-vs-sglang"},{"title":"Benchmark LLM inference latency, throughput, and cost","sidebarTitle":"Benchmark latency and cost","href":"/guides/inference/benchmarking"},{"title":"How to enable and measure vLLM prefix caching","sidebarTitle":"Prefix caching and KV cache","href":"/guides/inference/prefix-caching"},{"title":"When does speculative decoding speed up LLM inference?","sidebarTitle":"Speculative decoding","href":"/guides/inference/speculative-decoding"}]},{"group":"Inference How-to Guides","pages":[{"title":"How to reduce LLM inference cost: a practical workflow","sidebarTitle":"Reduce inference cost","href":"/guides/inference/how-to/reduce-cost"},{"title":"How to run a 4-bit quantized LLM with vLLM","sidebarTitle":"Run a quantized LLM","href":"/guides/inference/how-to/quantization-vllm"},{"title":"How to run vLLM on AMD GPUs with ROCm","sidebarTitle":"Run vLLM on AMD GPUs","href":"/guides/inference/how-to/amd-vllm"},{"title":"How to serve LLMs on AWS Inferentia and Trainium with vLLM","sidebarTitle":"Serve LLMs with AWS Neuron","href":"/guides/inference/how-to/aws-neuron-vllm"},{"title":"How to run LLM inference on Google TPUs with vLLM","sidebarTitle":"Serve an LLM on Google TPU","href":"/guides/inference/how-to/google-tpu-vllm"},{"title":"How to run a local LLM on Apple silicon with MLX","sidebarTitle":"Run an LLM on Apple silicon","href":"/guides/inference/how-to/apple-silicon-mlx"},{"title":"How to run LLM inference on a CPU with llama.cpp","sidebarTitle":"Run an LLM on a CPU","href":"/guides/inference/how-to/cpu-llama-cpp"},{"title":"How to compare Groq, Cerebras, and SambaNova inference APIs","sidebarTitle":"Compare specialized inference APIs","href":"/guides/inference/how-to/compare-inference-apis"}]},{"group":"Inference Hardware","pages":[{"title":"NVIDIA alternatives for LLM inference","sidebarTitle":"Choose inference hardware","href":"/guides/inference/hardware/overview"},{"title":"AMD GPU inference: understand ROCm and vLLM","sidebarTitle":"AMD GPUs and ROCm","href":"/guides/inference/hardware/amd-rocm"},{"title":"AWS Inferentia vs Trainium for LLM inference","sidebarTitle":"AWS Inferentia and Trainium","href":"/guides/inference/hardware/aws-neuron"},{"title":"TPU vs GPU for LLM inference: what changes?","sidebarTitle":"Google TPUs","href":"/guides/inference/hardware/google-tpu"},{"title":"Groq vs Cerebras vs SambaNova: inference architectures","sidebarTitle":"Groq, Cerebras, and SambaNova","href":"/guides/inference/hardware/specialized-accelerators"},{"title":"LLM inference on CPUs and Apple silicon","sidebarTitle":"CPUs and Apple silicon","href":"/guides/inference/hardware/cpu-apple-silicon"}]},{"group":"Concepts","pages":[{"title":"Deployments","href":"/concepts/deployments"},{"title":"Job Queues","href":"/concepts/job_queues"},{"title":"Fine-tune LoRA adapters with the Tensorfuse SDK","sidebarTitle":"Finetuning","href":"/concepts/finetuning"},{"title":"Dev Containers","href":"/concepts/devcontainers"},{"title":"Volumes","href":"/concepts/volumes"}]},{"group":"Operations","pages":[{"title":"Deployment Configuration","href":"/concepts/configuration"},{"title":"Secrets","href":"/concepts/secrets"},{"title":"Environments","href":"/concepts/environments"},{"title":"Custom domains with TLS","sidebarTitle":"Custom Domains","href":"/concepts/custom_domains_with_tls"},{"title":"Debugging Tensorfuse Deployments and Jobs with logs","sidebarTitle":"Logs","href":"/concepts/observability/debugging_with_logs"},{"title":"Using Tensorkube with Github Actions","sidebarTitle":"GitHub Actions","href":"/concepts/github_actions"},{"title":"Adding Other Members","href":"/concepts/adding_members"}]},{"group":"Troubleshooting","pages":[{"title":"Troubleshooting","href":"/concepts/troubleshooting"},{"title":"Handling Node Failures","href":"/concepts/node_failures"}]},{"group":"Enterprise Setup","pages":[{"title":"Sub-accounts","href":"/enterprise/sub_account_setup"}]},{"group":"Architecture","pages":[{"title":"How Tensorfuse cluster configuration works","sidebarTitle":"Configure","href":"/concepts/architecture/configure"},{"title":"How Tensorfuse builds deployment images","sidebarTitle":"Build","href":"/concepts/architecture/build"},{"title":"How Tensorfuse serves inference requests","sidebarTitle":"Serve","href":"/concepts/architecture/serve"},{"title":"How Tensorfuse queued jobs run","sidebarTitle":"Jobs","href":"/concepts/architecture/jobs"}]}]},{"tab":"Examples","groups":[{"group":"Large Language Models","pages":[{"title":"Deploy GPT-OSS 20B and 120B on AWS with vLLM","sidebarTitle":"Self-host GPT-OSS on AWS","href":"/guides/modality/text/openai_oss"},{"title":"Deploy Llama 4 Models on your AWS account","sidebarTitle":"Deploy production-ready Llama 4 on AWS","href":"/guides/modality/text/llama_4"},{"title":"Deploy Llama-3.3-70B-Instruct on Serverless GPUs","sidebarTitle":"Deploy a production ready LLM service using vLLM","href":"/guides/llama_guide"},{"title":"Llama 3.1 70B fine-tuning with LoRAX (legacy)","href":"/guides/finetuning_llama_70b"},{"title":"Finetuning using Axolotl on your AWS Account","href":"/guides/axolotl_finetuning_guide"},{"title":"Deploy Deepseek R1 671B on Serverless GPUs","sidebarTitle":"Deploy a production-ready DeepSeek R1 service using vLLM","href":"/guides/deepseek_r1"},{"title":"Deploying Pixtral-12B-Quantised-4-Bit on Serverless GPUs","href":"/guides/pixtral_12b_quantized_4bit"},{"title":"Deploy Jina Embeddings model on your AWS","href":"/guides/jina_embeddings"},{"title":"Deploy GGUF quants of Deepseek R1 671B on Serverless GPUs","sidebarTitle":"Deploy a production-ready llama.cpp service","href":"/guides/integrations/llama_cpp"},{"title":"Deploy Qwen QwQ 32B on Serverless GPUs","sidebarTitle":"Deploy Qwen QwQ 32B service using vLLM","href":"/guides/reasoning/qwen_qwq"},{"title":"Transforming Qwen 7B into Your Own Reasoning Model","href":"/guides/reasoning/unsloth/qwen7b"}]},{"group":"Image and Video Models","pages":[{"title":"Deploying Stable Diffusion 3 Medium on Serverless GPUs","href":"/guides/sd3_medium"},{"title":"Deploy Stable Diffusion XL model using ComfyUI on your AWS","href":"/guides/comfyui_stable_diffusion_xl"},{"title":"Deploying FLUX.1-dev on Serverless GPUs","href":"/guides/modality/image/flux_dev"},{"title":"Deploy Mochi 1 Preview Video Model using ComfyUI on your AWS","href":"/guides/mochi_comfy"},{"title":"Run SAM2 on your own AWS on Serverless GPUs","href":"/guides/SAM2"},{"title":"Deploying Resnet on serverless GPUs","href":"/guides/resnet_deployment"}]},{"group":"Audio Models","pages":[{"title":"Deploying SpeechT5 on serverless GPUs","href":"/guides/tts_depl"},{"title":"Deploying Sesame-CSM-1B on Serverless GPUs","href":"/guides/modality/audio/sesame-csm-1b"}]},{"group":"Miscellaneous","pages":[{"title":"Cheatsheet for Tensorkube users","href":"/guides/cheatsheet"},{"title":"Install AWS-CLI on Mac OS","href":"/guides/aws_cli"}]}]},{"tab":"Reference","groups":[{"group":"CLI Reference","pages":[{"title":"tensorkube account","sidebarTitle":"tensorkube account","href":"/reference/cli_reference/tensorkube_account"},{"title":"tensorkube cluster","sidebarTitle":"tensorkube cluster","href":"/reference/cli_reference/tensorkube_cluster"},{"title":"tensorkube configure","sidebarTitle":"tensorkube configure","href":"/reference/cli_reference/tensorkube_configure"},{"title":"tensorkube datasets","sidebarTitle":"tensorkube datasets","href":"/reference/cli_reference/tensorkube_datasets"},{"title":"tensorkube deploy","sidebarTitle":"tensorkube deploy","href":"/reference/cli_reference/tensorkube_deploy"},{"title":"tensorkube deployment","sidebarTitle":"tensorkube deployment","href":"/reference/cli_reference/tensorkube_deployment"},{"title":"tensorkube dev","sidebarTitle":"tensorkube dev","href":"/reference/cli_reference/tensorkube_dev"},{"title":"tensorkube domain","sidebarTitle":"tensorkube domain","href":"/reference/cli_reference/tensorkube_domain"},{"title":"tensorkube environment","sidebarTitle":"tensorkube environment","href":"/reference/cli_reference/tensorkube_environment"},{"title":"tensorkube get-permissions-command","sidebarTitle":"tensorkube get-permissions-command","href":"/reference/cli_reference/tensorkube_get_permissions_command"},{"title":"tensorkube get-principal-arn","sidebarTitle":"tensorkube get-principal-arn","href":"/reference/cli_reference/tensorkube_get_principal_arn"},{"title":"tensorkube give-cluster-access","sidebarTitle":"tensorkube give-cluster-access","href":"/reference/cli_reference/tensorkube_give_cluster_access"},{"title":"tensorkube install-prerequisites","sidebarTitle":"tensorkube install-prerequisites","href":"/reference/cli_reference/tensorkube_install_prerequisites"},{"title":"tensorkube job","sidebarTitle":"tensorkube job","href":"/reference/cli_reference/tensorkube_job"},{"title":"tensorkube list","sidebarTitle":"tensorkube list","href":"/reference/cli_reference/tensorkube_list"},{"title":"tensorkube login","sidebarTitle":"tensorkube login","href":"/reference/cli_reference/tensorkube_login"},{"title":"tensorkube reset","sidebarTitle":"tensorkube reset","href":"/reference/cli_reference/tensorkube_reset"},{"title":"tensorkube secret","sidebarTitle":"tensorkube secret","href":"/reference/cli_reference/tensorkube_secret"},{"title":"tensorkube sync","sidebarTitle":"tensorkube sync","href":"/reference/cli_reference/tensorkube_sync"},{"title":"tensorkube teardown","sidebarTitle":"tensorkube teardown","href":"/reference/cli_reference/tensorkube_teardown"},{"title":"tensorkube train","sidebarTitle":"tensorkube train","href":"/reference/cli_reference/tensorkube_train"},{"title":"tensorkube upgrade","sidebarTitle":"tensorkube upgrade","href":"/reference/cli_reference/tensorkube_upgrade"},{"title":"tensorkube version","sidebarTitle":"tensorkube version","href":"/reference/cli_reference/tensorkube_version"},{"title":"tensorkube volume","sidebarTitle":"tensorkube volume","href":"/reference/cli_reference/tensorkube_volume"}]},{"group":"Permissions","pages":[{"title":"Permissions to connect Tensorfuse to your account","sidebarTitle":"Permissions to Connect to Tensorfuse","href":"/reference/permissions/frontend_connect_permissions"},{"title":"Permissions for Configure","sidebarTitle":"Permissions for Configure","href":"/reference/permissions/configure_permissions"}]},{"group":"Changelog","pages":[{"title":"Changelog","sidebarTitle":"Changelog","href":"/reference/changelog/changelog"}]}]},{"tab":"Blog","pages":[{"title":"AI inference and GPU infrastructure engineering","href":"/blogs/blog"},{"group":"Agent infrastructure","pages":[{"title":"Agent Drive: Storage for the next Trillion agents","sidebarTitle":"State of agent storage","href":"/blogs/agent-drive"}]},{"group":"DeepSeek V4.1 Flash","pages":[{"title":"DeepSeek V4.1 Flash: why it matters and why inference is cheaper","sidebarTitle":"DeepSeek V4.1 Flash architecture","href":"/blogs/deepseek-v41-flash-architecture"},{"title":"How to self-host DeepSeek V4.1 Flash: AWS, Azure, hardware and cost","sidebarTitle":"DeepSeek V4.1 deployment and cost","href":"/blogs/deepseek-v41-flash-self-hosting-cost"}]},{"group":"Inference decisions","pages":[{"title":"How to calculate LLM inference cost per successful request","sidebarTitle":"Inference cost per request","href":"/blogs/inference-cost-per-request"},{"title":"When does GPU scale-to-zero save money for LLM inference?","sidebarTitle":"Scale-to-zero economics","href":"/blogs/scale-to-zero-gpu-inference"},{"title":"Lazy loading GPU containers: why startup is not readiness","sidebarTitle":"Lazy loading and the first request","mode":"wide","href":"/blogs/inference_on_k8s_1"},{"title":"Samagra Sharma","href":"/authors/samagra-sharma"}]},{"group":"Other posts","pages":[{"title":"CloudFormation won't fix your life but it can fix your infra","sidebarTitle":"Understanding AWS CloudFormation","mode":"wide","href":"/blogs/understanding_cfn"},{"title":"Lazy loading isn’t the magic pill to fix AI Inference","sidebarTitle":"Practical Lazy Loading Gains","mode":"wide","href":"/blogs/lazy_loading_performance_degradation"},{"title":"Reduce vLLM GPU cold start time on Kubernetes","sidebarTitle":"Reducing GPU Cold Start Time","mode":"wide","href":"/blogs/reducing_gpu_cold_start"},{"title":"Small Language Models are the Future of Agentic AI","sidebarTitle":"SLMs are the Future of Agentic AI","mode":"wide","href":"/blogs/small_language_model"},{"title":"Handling Unhealthy Nodes in EKS","sidebarTitle":"Fixing unhealthy EKS nodes","mode":"wide","href":"/blogs/handling_unhealthy_nodes_in_eks"},{"title":"Understanding Multi GPU Communication and Nvidia NCCL for finetuning models","sidebarTitle":"Multi GPU communication","mode":"wide","href":"/blogs/multi_gpu_communication_while_training"},{"title":"Introducing Fastpull: Start AI containers in seconds","sidebarTitle":"","mode":"wide","href":"/blogs/snapshotter_graphs"}]}]}]},"siteName":"Tensorfuse","docsConfig":{"theme":"mint","$schema":"https://mintlify.com/docs.json","name":"Tensorfuse","description":"Deploy and scale AI models in your AWS account. Guides to serverless GPU inference, vLLM, model serving, benchmarking, and finetuning with Tensorfuse.","colors":{"primary":"#EC5528","light":"#EC5528","dark":"#EC5528"},"logo":{"light":"https://mintcdn.com/tensorfuse-docs/dmj8dBJTiBMtkrNL/logo/logoFullwidth.png?fit=max\u0026auto=format\u0026n=dmj8dBJTiBMtkrNL\u0026q=85\u0026s=055e86590676b786ef5d267c6c430d76","dark":"https://mintcdn.com/tensorfuse-docs/dmj8dBJTiBMtkrNL/logo/logo_dark_mode.png?fit=max\u0026auto=format\u0026n=dmj8dBJTiBMtkrNL\u0026q=85\u0026s=5562a2c658f07e30317caae365ebe466"},"favicon":"https://mintcdn.com/tensorfuse-docs/dmj8dBJTiBMtkrNL/tf_logo.svg?fit=max\u0026auto=format\u0026n=dmj8dBJTiBMtkrNL\u0026q=85\u0026s=85803d36945990b7a2c8a2ca577b673c","appearance":{"default":"dark","strict":true},"background":{"color":{"dark":"#1D1D1D"}},"navbar":{"links":[{"href":"https://join.slack.com/t/tensorfusecommunity/shared_invite/zt-30r6ik3dz-Rf7nS76vWKOu6DoKh5Cs5w","label":"Community"}],"primary":{"type":"button","label":"Get Started","href":"https://app.tensorfuse.io/"}},"footer":{"socials":{"twitter":"https://twitter.com/tensorfuse","github":"https://github.com/tensorfuse","linkedin":"https://www.linkedin.com/company/tensorfuse"}},"seo":{"metatags":{"canonical":"https://tensorfuse.io/docs","og:site_name":"Tensorfuse Documentation","twitter:card":"summary_large_image","twitter:site":"@tensorfuse"}},"integrations":{"intercom":{"appId":"y9yz9hjf"},"mixpanel":{"projectToken":"754ffdc145ee654685ea74ac0fb18084"}},"contextual":{"options":["copy","view","chatgpt","claude"],"display":"header"},"styling":{"latex":true},"navigation":{"pages":[]}},"deployment":{"deploymentMetadataValue":{"subdomain":"tensorfuse-docs","hasAudioNarration":false,"actualSubdomain":"tensorfuse-docs","customDomains":["tensorfuse.io"],"gitSource":{"type":"github","owner":"samagra14","repo":"docs","deployBranch":"main","contentDirectory":"","isPrivate":true,"mountPath":"","label":""},"chroma":{"liveDeploymentHistoryId":"6adbe5ab1578ba4c8e43bd3c","collectionId":"b6931ea0-d536-443a-8d2a-793f74586ec7","schemaVersion":"v3","latestBuiltDeploymentHistoryId":"6adbe5ab1578ba4c8e43bd3c"},"entitlements":{"AI_CHAT":{"status":"ENABLED"},"WEB_MCP":{"status":"ENABLED"},"NARRATION":{"status":"ENABLED"}},"buildId":"6adbe5ab1578ba4c8e43bd3c","clientVersion":"0.0.4054","searchFilterCounts":[{"language":"default","tag":"Documentation","count":41},{"language":"default","tag":"Reference","count":27},{"language":"default","tag":"CLI Reference","count":24},{"language":"default","tag":"Examples","count":21},{"language":"default","tag":"Blog","count":15},{"language":"default","tag":"Large Language Models","count":11},{"language":"default","tag":"Inference How-to Guides","count":8},{"language":"default","tag":"Other posts","count":7},{"language":"default","tag":"Operations","count":7},{"language":"default","tag":"Image and Video Models","count":6}]},"assistantConfig":{},"basePath":"/docs","hasChatPermissions":true,"hasWebMcpPermissions":true,"toggles":[{"name":"kill-isr","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":"llms-txt-v2","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":"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":"vite-origin","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":"sso-setup-deadline-banner","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false}],"googleFontsInlined":false},"customCss":[{"filePath":"custom.css","content":""}],"page":{"pagePath":"reference/tensorkube_deploy","slug":"/reference/tensorkube_deploy","pageMetadata":{"title":"Page Not Found","mode":"custom","robots":"noindex, nofollow","noindex":true},"notFound":true,"subdomain":"tensorfuse-docs","jsLinks":["/docs/_mintlify/custom/tensorfuse-docs/c3dc9745059fca0c/warmly.js"],"siteName":"Tensorfuse","title":"Page Not Found"},"headHtml":"\u003cscript data-mint-head>(function(){var d=document.documentElement,p=\"dark\";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=\"dark\"}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=\"application-name\" content=\"Tensorfuse\">\u003cmeta data-mint-head name=\"generator\" content=\"Mintlify\">\u003cmeta data-mint-head name=\"robots\" content=\"noindex, nofollow\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/docs/mintlify-assets/_mintlify/favicons/tensorfuse-docs/gleo0vHV9BrLVCDe/_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=\"/docs/mintlify-assets/_mintlify/favicons/tensorfuse-docs/gleo0vHV9BrLVCDe/_generated/favicon/apple-touch-icon.png\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/docs/mintlify-assets/_mintlify/favicons/tensorfuse-docs/gleo0vHV9BrLVCDe/_generated/favicon/favicon-16x16.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/docs/mintlify-assets/_mintlify/favicons/tensorfuse-docs/gleo0vHV9BrLVCDe/_generated/favicon/favicon-32x32.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/docs/mintlify-assets/_mintlify/favicons/tensorfuse-docs/gleo0vHV9BrLVCDe/_generated/favicon/favicon.ico\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/docs/mintlify-assets/_mintlify/favicons/tensorfuse-docs/gleo0vHV9BrLVCDe/_generated/favicon-dark/android-chrome-192x192.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/docs/mintlify-assets/_mintlify/favicons/tensorfuse-docs/gleo0vHV9BrLVCDe/_generated/favicon-dark/favicon-16x16.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/docs/mintlify-assets/_mintlify/favicons/tensorfuse-docs/gleo0vHV9BrLVCDe/_generated/favicon-dark/favicon-32x32.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/docs/mintlify-assets/_mintlify/favicons/tensorfuse-docs/gleo0vHV9BrLVCDe/_generated/favicon-dark/favicon.ico\" media=\"(prefers-color-scheme: dark)\">\u003cmeta data-mint-head name=\"msapplication-config\" content=\"/docs/mintlify-assets/_mintlify/favicons/tensorfuse-docs/gleo0vHV9BrLVCDe/_generated/favicon/browserconfig.xml\">\u003cmeta data-mint-head name=\"apple-mobile-web-app-title\" content=\"Tensorfuse\">\u003cmeta data-mint-head name=\"msapplication-TileColor\" content=\"#EC5528\">\u003cmeta data-mint-head name=\"mode\" content=\"custom\">\u003clink data-mint-head rel=\"alternate\" type=\"application/xml\" href=\"/docs/sitemap.xml\">\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"name\":\"Tensorfuse\",\"creator\":{\"@type\":\"Organization\",\"name\":\"Mintlify\",\"url\":\"https://mintlify.com\"}}\u003c/script>","basePath":"","title":"Page Not Found","buildId":"dpl_GWQzn6k13MqphA3qck3hQKoQXDzM","deploymentId":"dpl_GWQzn6k13MqphA3qck3hQKoQXDzM","dynamics":["09d3a20edf"],"chunks":["NotFoundPage-DjTRFW6g.js","NotFoundHydrator-BDh9rChY.js"]}
