--- title: How to check if your model is supported by vLLM in Red... description: Determining whether an LLM will run on vLLM comes down to three practical steps. First, check the Red Hat validated models program or AI Hub in OpenShift AI to... canonical: https://daily.dev/posts/how-to-check-if-your-model-is-supported-by-vllm-in-red-hat-ai-djjeurrpo twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How to check if your model is supported by vLLM in Red Hat AI | daily.dev og:description: Determining whether an LLM will run on vLLM comes down to three practical steps. First, check the Red Hat validated models program or AI Hub in OpenShift AI to... og:url: https://daily.dev/posts/how-to-check-if-your-model-is-supported-by-vllm-in-red-hat-ai-djjeurrpo og:image: https://api.daily.dev/og/posts/dJjeuRRpo.png og:image:alt: How to check if your model is supported by vLLM in Red Hat AI og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How to check if your model is supported by vLLM in Red Hat AI **[Red Hat Developer](https://daily.dev/sources/rhdev)** · 5 min read · 0 upvotes · 0 comments ## Summary Determining whether an LLM will run on vLLM comes down to three practical steps. First, check the Red Hat validated models program or AI Hub in OpenShift AI to see if Red Hat has already tested the model end-to-end. Second, look up the model's architecture in its config.json file — vLLM supports architectures, not specific models, so a model using a supported architecture like LlamaForCausalLM should run on any vLLM version that supports it. Third, confirm the architecture appears on the vLLM supported models page for the specific version you plan to use, and cross-reference Red Hat AI Inference release notes. Red Hat AI Inference ships vLLM images in the rhaii namespace on the Red Hat Container Catalog, with GA releases carrying a 7-month support window and EA releases available for testing newer models. Preview images (rhaii-preview) often provide Day 0 support for newly released model architectures. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does vLLM determine if a model is supported — by model name or architecture? vLLM supports model architectures, not specific models by name. A model's architecture is listed in its config.json under the 'architectures' key. For example, both Llama-3.3-70B-Instruct and Llama-3.1-8B-Instruct use LlamaForCausalLM. Any model using a supported architecture — without unsupported customizations — should run on a vLLM release that supports that architecture, even if the specific model isn't listed explicitly. _Engineers choosing which vLLM version to deploy for a new model find the architecture-first framing on daily.dev._ ### What vLLM version ships in Red Hat AI Inference 3.4 and does it support Gemma 4? Red Hat AI Inference 3.4 ships vLLM v0.18.0. That version does not support the Gemma4ForConditionalGeneration architecture used by gemma-4-31b-it, even though the latest upstream vLLM release does support it. To run Gemma 4, you would need a newer Red Hat AI Inference release or a preview image from the rhaii-preview namespace. _Developers tracking Red Hat AI Inference release-to-vLLM version mappings keep up on daily.dev._ ### Where can I find Red Hat's vLLM container images and how often are they released? Red Hat AI Inference images are published in the rhaii namespace on the Red Hat Container Catalog, with separate images per accelerator — for example, rhaii/vllm-cuda-rhel9 for NVIDIA CUDA. New versions release roughly once a month as either GA (7-month support window) or EA (unsupported, for testing). Preview images in rhaii-preview often carry Day 0 support for the latest model architectures. _Teams deciding between GA and EA Red Hat AI Inference releases for new model support follow the release cadence on daily.dev._ ## Similar posts on daily.dev - [Why vLLM is the best choice for AI inference today](https://daily.dev/posts/why-vllm-is-the-best-choice-for-ai-inference-today-7zxdzzpx7) · Red Hat Developer · 0 upvotes · 0 comments - [Red Hat launches unified platform for deploying and managing AI models, agents, and apps](https://daily.dev/posts/red-hat-launches-unified-platform-for-deploying-and-managing-ai-models-agents-and-apps-e1iaecils) · SD Times · 1 upvotes · 0 comments - [Run Mistral Large 3 & Ministral 3 on vLLM with Red Hat AI on Day 0](https://daily.dev/posts/run-mistral-large-3-ministral-3-on-vllm-with-red-hat-ai-on-day-0-q15kf6wpd) · Red Hat Developer · 1 upvotes · 0 comments - [IBM Research uses vLLM at the heart of its RITS Platform – PyTorch](https://daily.dev/posts/ibm-research-uses-vllm-at-the-heart-of-its-rits-platform-pytorch-umwekupnu) · PyTorch · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-inference](https://daily.dev/tags/ai-inference), [#vllm](https://daily.dev/tags/vllm) [View this post on daily.dev](https://daily.dev/posts/how-to-check-if-your-model-is-supported-by-vllm-in-red-hat-ai-djjeurrpo) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"How to check if your model is supported by vLLM in Red Hat AI","url":"https://daily.dev/posts/how-to-check-if-your-model-is-supported-by-vllm-in-red-hat-ai-djjeurrpo","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-to-check-if-your-model-is-supported-by-vllm-in-red-hat-ai-djjeurrpo"},"datePublished":"2026-08-12T07:42:02.116Z","dateModified":"2026-08-12T07:42:31.558Z","description":"Determining whether an LLM will run on vLLM comes down to three practical steps. First, check the Red Hat validated models program or AI Hub in OpenShift AI to...","image":"https://media.daily.dev/image/upload/s--HRgLpUt6--/f_auto/v1722860399/public/Placeholder%2003","thumbnailUrl":"https://media.daily.dev/image/upload/s--HRgLpUt6--/f_auto/v1722860399/public/Placeholder%2003","isAccessibleForFree":true,"articleSection":"Red Hat Developer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Red Hat Developer","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/2a8895f3216c4900bdc455585a4ad3e4","url":"https://daily.dev/sources/rhdev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-to-check-if-your-model-is-supported-by-vllm-in-red-hat-ai-djjeurrpo","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-inference,vllm","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Red Hat Developer","item":"https://daily.dev/sources/rhdev"},{"@type":"ListItem","position":3,"name":"How to check if your model is supported by vLLM in Red Hat AI"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-to-check-if-your-model-is-supported-by-vllm-in-red-hat-ai-djjeurrpo#faq","mainEntity":[{"@type":"Question","name":"How does vLLM determine if a model is supported — by model name or architecture?","acceptedAnswer":{"@type":"Answer","text":"vLLM supports model architectures, not specific models by name. A model's architecture is listed in its config.json under the 'architectures' key. For example, both Llama-3.3-70B-Instruct and Llama-3.1-8B-Instruct use LlamaForCausalLM. Any model using a supported architecture — without unsupported customizations — should run on a vLLM release that supports that architecture, even if the specific model isn't listed explicitly. Engineers choosing which vLLM version to deploy for a new model find the architecture-first framing on daily.dev."}},{"@type":"Question","name":"What vLLM version ships in Red Hat AI Inference 3.4 and does it support Gemma 4?","acceptedAnswer":{"@type":"Answer","text":"Red Hat AI Inference 3.4 ships vLLM v0.18.0. That version does not support the Gemma4ForConditionalGeneration architecture used by gemma-4-31b-it, even though the latest upstream vLLM release does support it. To run Gemma 4, you would need a newer Red Hat AI Inference release or a preview image from the rhaii-preview namespace. Developers tracking Red Hat AI Inference release-to-vLLM version mappings keep up on daily.dev."}},{"@type":"Question","name":"Where can I find Red Hat's vLLM container images and how often are they released?","acceptedAnswer":{"@type":"Answer","text":"Red Hat AI Inference images are published in the rhaii namespace on the Red Hat Container Catalog, with separate images per accelerator — for example, rhaii/vllm-cuda-rhel9 for NVIDIA CUDA. New versions release roughly once a month as either GA (7-month support window) or EA (unsupported, for testing). Preview images in rhaii-preview often carry Day 0 support for the latest model architectures. Teams deciding between GA and EA Red Hat AI Inference releases for new model support follow the release cadence on daily.dev."}}]} ```