--- title: Intel Updates LLM-Scaler-vLLM Build For vLLM 0.26 &... description: Intel released a new beta of LLM-Scaler-vLLM (0.26.0-b1), a Docker-based deployment for running vLLM on Intel Arc Pro GPUs. It rebases against upstream vLLM... canonical: https://daily.dev/posts/intel-updates-llm-scaler-vllm-build-for-vllm-0-26-other-improvements-p6sje4dlh twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Intel Updates LLM-Scaler-vLLM Build For vLLM 0.26 & Other Improvements | daily.dev og:description: Intel released a new beta of LLM-Scaler-vLLM (0.26.0-b1), a Docker-based deployment for running vLLM on Intel Arc Pro GPUs. It rebases against upstream vLLM... og:url: https://daily.dev/posts/intel-updates-llm-scaler-vllm-build-for-vllm-0-26-other-improvements-p6sje4dlh og:image: https://api.daily.dev/og/posts/P6sjE4DlH.png og:image:alt: Intel Updates LLM-Scaler-vLLM Build For vLLM 0.26 & Other Improvements 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. # Intel Updates LLM-Scaler-vLLM Build For vLLM 0.26 & Other Improvements **[Phoronix](https://daily.dev/sources/phoronix)** · 1 min read · 0 upvotes · 0 comments ## Summary Intel released a new beta of LLM-Scaler-vLLM (0.26.0-b1), a Docker-based deployment for running vLLM on Intel Arc Pro GPUs. It rebases against upstream vLLM 0.26, which added DeepSeek-V4 kernel support, improved KV offloading, and JIT warm-up infrastructure. The update also improves time-to-first-token for Qwen models, boosts FP8 KV cache performance, and fixes various bugs. Downloads are available on GitHub. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What's new in Intel's LLM-Scaler-vLLM 0.26.0-b1 beta release? LLM-Scaler-vLLM 0.26.0-b1 rebases against upstream vLLM 0.26, which adds DeepSeek-V4 kernel support, improved KV offloading, and JIT warm-up infrastructure. The Intel-specific build also improves time-to-first-token for Qwen models, boosts FP8 KV cache performance, and fixes several bugs. It provides a Docker-based setup for running vLLM on Intel Arc Pro graphics hardware. _Teams running LLM inference on Intel GPUs can track vLLM version bumps like this on daily.dev._ ### What does vLLM 0.26 add for DeepSeek models? vLLM 0.26 adds kernel support for DeepSeek-V4, alongside improved KV cache offloading, JIT warm-up infrastructure, and other performance optimizations. Intel's LLM-Scaler-vLLM 0.26.0-b1 build incorporates these upstream changes for deployment on Arc Pro GPUs. _Anyone deciding on an inference stack for new model releases can follow vLLM updates on daily.dev._ ## Similar posts on daily.dev - [Intel-Scaler-vLLM 0.21.0-b1 Delivers Latest Features For vLLM On Intel GPUs](https://daily.dev/posts/intel-scaler-vllm-0-21-0-b1-delivers-latest-features-for-vllm-on-intel-gpus-hgv8mgtsj) · Phoronix · 0 upvotes · 0 comments - [Intel Releases LLM-Scaler-vLLM 1.3 With New LLM Model Support](https://daily.dev/posts/intel-releases-llm-scaler-vllm-1-3-with-new-llm-model-support-obfisnxhg) · Phoronix · 1 upvotes · 0 comments - [Intel LLM-Scaler vllm-0.14.0-b8.2 Released With Official Arc Pro B70 Support](https://daily.dev/posts/intel-llm-scaler-vllm-0-14-0-b8-2-released-with-official-arc-pro-b70-support-ru9wzc0rd) · Phoronix · 0 upvotes · 0 comments --- Tags: [#docker](https://daily.dev/tags/docker), [#gpu](https://daily.dev/tags/gpu), [#ai-inference](https://daily.dev/tags/ai-inference), [#vllm](https://daily.dev/tags/vllm) [View this post on daily.dev](https://daily.dev/posts/intel-updates-llm-scaler-vllm-build-for-vllm-0-26-other-improvements-p6sje4dlh) ```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":"Intel Updates LLM-Scaler-vLLM Build For vLLM 0.26 & Other Improvements","url":"https://daily.dev/posts/intel-updates-llm-scaler-vllm-build-for-vllm-0-26-other-improvements-p6sje4dlh","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/intel-updates-llm-scaler-vllm-build-for-vllm-0-26-other-improvements-p6sje4dlh"},"datePublished":"2026-09-02T10:06:29.068Z","dateModified":"2026-09-02T10:07:11.801Z","description":"Intel released a new beta of LLM-Scaler-vLLM (0.26.0-b1), a Docker-based deployment for running vLLM on Intel Arc Pro GPUs. It rebases against upstream vLLM...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a4807b354b7c996b01059e13a4cf539e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a4807b354b7c996b01059e13a4cf539e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Phoronix","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":"Phoronix","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/6a26ba379dd64932830aa0c9803dd7ee","url":"https://daily.dev/sources/phoronix"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/intel-updates-llm-scaler-vllm-build-for-vllm-0-26-other-improvements-p6sje4dlh","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"docker,gpu,ai-inference,vllm","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Phoronix","item":"https://daily.dev/sources/phoronix"},{"@type":"ListItem","position":3,"name":"Intel Updates LLM-Scaler-vLLM Build For vLLM 0.26 & Other Improvements"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/intel-updates-llm-scaler-vllm-build-for-vllm-0-26-other-improvements-p6sje4dlh#faq","mainEntity":[{"@type":"Question","name":"What's new in Intel's LLM-Scaler-vLLM 0.26.0-b1 beta release?","acceptedAnswer":{"@type":"Answer","text":"LLM-Scaler-vLLM 0.26.0-b1 rebases against upstream vLLM 0.26, which adds DeepSeek-V4 kernel support, improved KV offloading, and JIT warm-up infrastructure. The Intel-specific build also improves time-to-first-token for Qwen models, boosts FP8 KV cache performance, and fixes several bugs. It provides a Docker-based setup for running vLLM on Intel Arc Pro graphics hardware. Teams running LLM inference on Intel GPUs can track vLLM version bumps like this on daily.dev."}},{"@type":"Question","name":"What does vLLM 0.26 add for DeepSeek models?","acceptedAnswer":{"@type":"Answer","text":"vLLM 0.26 adds kernel support for DeepSeek-V4, alongside improved KV cache offloading, JIT warm-up infrastructure, and other performance optimizations. Intel's LLM-Scaler-vLLM 0.26.0-b1 build incorporates these upstream changes for deployment on Arc Pro GPUs. Anyone deciding on an inference stack for new model releases can follow vLLM updates on daily.dev."}}]} ```