{"id":8869,"date":"2026-11-13T12:25:15","date_gmt":"2026-11-13T12:25:15","guid":{"rendered":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches"},"modified":"2026-11-13T12:25:15","modified_gmt":"2026-11-13T12:25:15","slug":"cve-2026-126397-vllm-cohere2-vision-dos-max-patches","status":"publish","type":"post","link":"https:\/\/i10x.ai\/news\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches","title":{"rendered":"CVE-2026-126397: vLLM Cohere2 Vision DoS via Unbounded max_patches"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">A high-severity denial-of-service vulnerability in vLLM versions 0.10.1 through 0.30.x allows remote clients to exhaust preprocessing workers when serving Cohere2 Vision models by submitting small image requests with large, request-controlled max_patches values. The vendor released version 0.31.0 to fix the issue.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u26a1 Quick Take<\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li><strong>What:<\/strong> vLLM versions 0.10.1 through 0.30.x forward a request-controlled <code>mm_processor_kwargs.max_patches<\/code> value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing.<\/li><li><strong>Who is affected:<\/strong> Operators running vLLM Python OpenAI-compatible servers that serve Cohere2 Vision models and accept image chat-completion requests.<\/li><li><strong>Impact:<\/strong> Remote clients can send small image requests with large, varying <code>max_patches<\/code> values to bypass the LRU cache, exhaust preprocessing workers, substantially increase request latency, and deny service to other clients.<\/li><li><strong>Fixed version:<\/strong> 0.31.0<\/li><li><strong>What to do:<\/strong> Upgrade to vLLM 0.31.0 or later if you serve Cohere2 Vision models.<\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">In plain English<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">vLLM is a Python library that serves large language models, including vision models that process images. A flaw in versions 0.10.1 through 0.30.x lets anyone who can send image chat requests include a special parameter with a very large number. The server does not check this number before using it in a calculation that takes much longer for larger values. An attacker can send many small requests with different large numbers to overwhelm the server&#8217;s image-processing workers, making the service slow or unavailable for everyone else. If you run vLLM to serve Cohere2 Vision models, upgrade to version 0.31.0. If you do not use vLLM or do not serve Cohere2 Vision models, you can ignore this issue.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">What happened<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The vLLM project disclosed CVE-2026-126397 on October 27, 2026, and published details in GitHub Security Advisory GHSA-9g3c-x747-c6wr. The vulnerability affects vLLM versions from 0.10.1 up to but not including 0.31.0.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">When vLLM serves a Cohere2 Vision model through its Python OpenAI-compatible frontend, it accepts a <code>ChatCompletionRequest<\/code> that includes an optional <code>mm_processor_kwargs<\/code> dictionary. This dictionary is defined as an unrestricted <code>dict[str, Any]<\/code> and can contain a <code>max_patches<\/code> key with any positive integer value supplied by the client.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The server forwards this request-controlled value directly to the Hugging Face processor without applying a server-side upper bound. The processor then enumerates candidate tile aspect ratios using two nested loops, both of which have bounds controlled by <code>max_patches<\/code>. This design causes the preprocessing work to grow quadratically with the supplied value.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Because the expensive enumeration occurs during request preprocessing, before the request reaches normal model execution, a small request body can trigger work disproportionate to its size. Clients can also vary the <code>max_patches<\/code> value across requests to avoid reuse of the helper&#8217;s small LRU cache, further amplifying the impact.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The issue was rechecked on September 8, 2026, against upstream main commit <code>f6326f53bda46898a331c2d24500332c285d9a2b<\/code>. The vulnerable data flow was present at that revision.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">What you should do<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Upgrade to vLLM version 0.31.0 or later if you are running a vLLM server that serves Cohere2 Vision models and accepts image chat-completion requests.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The default vLLM server does not require an API key. If you have configured API authentication, exploitation requires a client authorized to call the affected endpoint. Review your access controls and logs for unusual patterns of image requests with large <code>mm_processor_kwargs.max_patches<\/code> values.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">What it means<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">CVE-2026-126397 is a high-severity denial-of-service vulnerability with a CVSS v3.1 score of 7.5 and a CVSS v4.0 score of 8.7. The flaw does not permit code execution, confidentiality impact, or integrity impact.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The issue is model-specific and affects only deployments serving Cohere2 Vision models. Operators serving other models or not using the multimodal preprocessing path are not affected.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The vulnerability demonstrates a common pitfall in AI serving infrastructure: accepting request-controlled computational budgets without server-side validation. The quadratic complexity of the preprocessing step, combined with the ability to bypass caching, makes this a practical denial-of-service vector for remote attackers.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Sources<\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li><a href=\"https:\/\/github.com\/vllm-project\/vllm\/security\/advisories\/GHSA-9g3c-x747-c6wr\" target=\"_blank\" rel=\"noreferrer noopener\">GitHub Security Advisory GHSA-9g3c-x747-c6wr<\/a><\/li><li><a href=\"https:\/\/nvd.nist.gov\/vuln\/detail\/CVE-2026-126397\" target=\"_blank\" rel=\"noreferrer noopener\">NVD CVE-2026-126397<\/a><\/li><li><a href=\"https:\/\/www.vulncheck.com\/advisories\/vllm-0.10.1-before-0.31.0-cohere2-vision-dos-via-max-patches\" target=\"_blank\" rel=\"noreferrer noopener\">VulnCheck Advisory: vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches<\/a><\/li><li><a href=\"https:\/\/github.com\/vllm-project\/vllm\/commit\/f6326f53bda46898a331c2d24500332c285d9a2b\" target=\"_blank\" rel=\"noreferrer noopener\">vLLM commit f6326f53<\/a><\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>A high-severity denial-of-service vulnerability in vLLM versions 0.10.1 through 0.30.x allows remote clients to exhaust preprocessing workers when serving Cohere2 Vision models by submitting small image requests with large, request-controlled max_patches values.<\/p>\n","protected":false},"author":2,"featured_media":8868,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"paper_title":"","paper_url":"","pdf_url":"","doi":"","arxiv_id":"","authors":"","institutions":"","paper_date":"","venue":"","peer_reviewed":false,"code_url":"","data_url":"","funding_coi":"","figure_license":"","paper_license":"","replication":"","study_models":"","study_sample":"","footnotes":"","_yoast_wpseo_primary_category":"65","_nx_sec_severity":"high","_nx_sec_affected":"vLLM 0.10.1 through 0.30.x serving Cohere2 Vision models","_nx_sec_status":"patch-available","_nx_sec_kicker":"URGENT: vLLM Cohere2 Vision DoS via unbounded preprocessing parameter","_nx_sec_type":"platform","_nx_sec_vendor":"vLLM","_nx_sec_fixed":"0.31.0","_nx_sec_action":""},"categories":[65,12,28],"tags":[],"companies":[],"products":[],"class_list":["post-8869","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-security","category-policy-safety","category-security-defense"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>CVE-2026-126397: vLLM Cohere2 Vision DoS Flaw<\/title>\n<meta name=\"description\" content=\"CVE-2026-126397 lets remote clients exhaust vLLM preprocessing workers serving Cohere2 Vision models by sending large max_patches values. Patch in 0.31.0.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"CVE-2026-126397: vLLM Cohere2 Vision DoS Flaw\" \/>\n<meta property=\"og:description\" content=\"CVE-2026-126397 lets remote clients exhaust vLLM preprocessing workers serving Cohere2 Vision models by sending large max_patches values. Patch in 0.31.0.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches\" \/>\n<meta property=\"og:site_name\" content=\"i10X News\" \/>\n<meta property=\"article:published_time\" content=\"2026-11-13T12:25:15+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/11\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches-title.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1344\" \/>\n\t<meta property=\"og:image:height\" content=\"768\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Christopher Ort\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/i10x-news-og-default-1200x630-1.png\" \/>\n<meta name=\"twitter:creator\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:site\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Christopher Ort\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches\"},\"author\":{\"name\":\"Christopher Ort\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\"},\"headline\":\"CVE-2026-126397: vLLM Cohere2 Vision DoS via Unbounded max_patches\",\"datePublished\":\"2026-11-13T12:25:15+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches\"},\"wordCount\":651,\"publisher\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches-title.webp\",\"articleSection\":[\"AI Security\",\"Policy &amp; Safety\",\"Security &amp; Defense\"],\"inLanguage\":\"en-US\",\"dateModified\":\"2026-11-13T12:25:15+00:00\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches\",\"url\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches\",\"name\":\"CVE-2026-126397: vLLM Cohere2 Vision DoS Flaw\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches-title.webp\",\"datePublished\":\"2026-11-13T12:25:15+00:00\",\"description\":\"CVE-2026-126397 lets remote clients exhaust vLLM preprocessing workers serving Cohere2 Vision models by sending large max_patches values. Patch in 0.31.0.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#primaryimage\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches-title.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches-title.webp\",\"width\":1344,\"height\":768,\"caption\":\"Image: AI-generated, i10X\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/i10x.ai\\\/news\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"CVE-2026-126397: vLLM Cohere2 Vision DoS via Unbounded max_patches\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#website\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\",\"name\":\"i10X News\",\"description\":\"Stay updated with the latest news and announcements from i10X.\",\"publisher\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/i10x.ai\\\/news?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\",\"name\":\"i10X\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"contentUrl\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"width\":180,\"height\":180,\"caption\":\"i10X\"},\"image\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/i10x_ai\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/i10x-ai\",\"https:\\\/\\\/instagram.com\\\/i10x.ai\",\"https:\\\/\\\/www.youtube.com\\\/@i10X_ai_official\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\",\"name\":\"Christopher Ort\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"caption\":\"Christopher Ort\"},\"description\":\"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/author\\\/christopher-ort\",\"sameAs\":[\"https:\\\/\\\/i10x.ai\\\/blog\\\/author\\\/christopher-ort\"],\"worksFor\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"alumniOf\":{\"@type\":\"EducationalOrganization\",\"name\":\"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)\",\"url\":\"https:\\\/\\\/www.fau.eu\"},\"subjectOf\":[{\"@type\":\"CreativeWork\",\"url\":\"https:\\\/\\\/papers.ssrn.com\\\/abstract=7426699\",\"name\":\"The Style Penalty: How AI Resume-Writing Tools Shape Outcomes in Automated Hiring Screens\"},{\"@type\":\"CreativeWork\",\"url\":\"https:\\\/\\\/www.heise.de\\\/news\\\/KI-Chatbots-bewerten-KI-Lebenslaeufe-Claude-findet-sich-besser-als-GPT-11317531.html\",\"name\":\"KI-Chatbots bewerten KI-Lebensl\u00e4ufe: Claude findet sich besser als GPT\"},{\"@type\":\"CreativeWork\",\"url\":\"https:\\\/\\\/t3n.de\\\/news\\\/bewerbung-schreiben-ki-5-fehler-1747190\\\/\",\"name\":\"Bewerbung mit KI schreiben: Diese 5 Fehler solltet ihr laut Studien vermeiden\"}]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"CVE-2026-126397: vLLM Cohere2 Vision DoS Flaw","description":"CVE-2026-126397 lets remote clients exhaust vLLM preprocessing workers serving Cohere2 Vision models by sending large max_patches values. Patch in 0.31.0.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches","og_locale":"en_US","og_type":"article","og_title":"CVE-2026-126397: vLLM Cohere2 Vision DoS Flaw","og_description":"CVE-2026-126397 lets remote clients exhaust vLLM preprocessing workers serving Cohere2 Vision models by sending large max_patches values. Patch in 0.31.0.","og_url":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches","og_site_name":"i10X News","article_published_time":"2026-11-13T12:25:15+00:00","og_image":[{"width":1344,"height":768,"url":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/11\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches-title.webp","type":"image\/webp"}],"author":"Christopher Ort","twitter_card":"summary_large_image","twitter_image":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/i10x-news-og-default-1200x630-1.png","twitter_creator":"@i10x_ai","twitter_site":"@i10x_ai","twitter_misc":{"Written by":"Christopher Ort","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#article","isPartOf":{"@id":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches"},"author":{"name":"Christopher Ort","@id":"https:\/\/i10x.ai\/news\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a"},"headline":"CVE-2026-126397: vLLM Cohere2 Vision DoS via Unbounded max_patches","datePublished":"2026-11-13T12:25:15+00:00","mainEntityOfPage":{"@id":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches"},"wordCount":651,"publisher":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"image":{"@id":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches-title.webp","articleSection":["AI Security","Policy &amp; Safety","Security &amp; Defense"],"inLanguage":"en-US","dateModified":"2026-11-13T12:25:15+00:00"},{"@type":"WebPage","@id":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches","url":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches","name":"CVE-2026-126397: vLLM Cohere2 Vision DoS Flaw","isPartOf":{"@id":"https:\/\/i10x.ai\/news\/#website"},"primaryImageOfPage":{"@id":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#primaryimage"},"image":{"@id":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches-title.webp","datePublished":"2026-11-13T12:25:15+00:00","description":"CVE-2026-126397 lets remote clients exhaust vLLM preprocessing workers serving Cohere2 Vision models by sending large max_patches values. Patch in 0.31.0.","breadcrumb":{"@id":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#primaryimage","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches-title.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches-title.webp","width":1344,"height":768,"caption":"Image: AI-generated, i10X"},{"@type":"BreadcrumbList","@id":"https:\/\/i10xnews.kinsta.cloud\/cve-2026-126397-vllm-cohere2-vision-dos-max-patches#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/i10x.ai\/news"},{"@type":"ListItem","position":2,"name":"CVE-2026-126397: vLLM Cohere2 Vision DoS via Unbounded max_patches"}]},{"@type":"WebSite","@id":"https:\/\/i10x.ai\/news\/#website","url":"https:\/\/i10x.ai\/news","name":"i10X News","description":"Stay updated with the latest news and announcements from i10X.","publisher":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/i10x.ai\/news?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/i10x.ai\/news\/#organization","name":"i10X","url":"https:\/\/i10x.ai\/news\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/#\/schema\/logo\/image\/","url":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","contentUrl":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","width":180,"height":180,"caption":"i10X"},"image":{"@id":"https:\/\/i10x.ai\/news\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/i10x_ai","https:\/\/www.linkedin.com\/company\/i10x-ai","https:\/\/instagram.com\/i10x.ai","https:\/\/www.youtube.com\/@i10X_ai_official"]},{"@type":"Person","@id":"https:\/\/i10x.ai\/news\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a","name":"Christopher Ort","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","caption":"Christopher Ort"},"description":"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.","url":"https:\/\/i10x.ai\/news\/author\/christopher-ort","sameAs":["https:\/\/i10x.ai\/blog\/author\/christopher-ort"],"worksFor":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"alumniOf":{"@type":"EducationalOrganization","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)","url":"https:\/\/www.fau.eu"},"subjectOf":[{"@type":"CreativeWork","url":"https:\/\/papers.ssrn.com\/abstract=7426699","name":"The Style Penalty: How AI Resume-Writing Tools Shape Outcomes in Automated Hiring Screens"},{"@type":"CreativeWork","url":"https:\/\/www.heise.de\/news\/KI-Chatbots-bewerten-KI-Lebenslaeufe-Claude-findet-sich-besser-als-GPT-11317531.html","name":"KI-Chatbots bewerten KI-Lebensl\u00e4ufe: Claude findet sich besser als GPT"},{"@type":"CreativeWork","url":"https:\/\/t3n.de\/news\/bewerbung-schreiben-ki-5-fehler-1747190\/","name":"Bewerbung mit KI schreiben: Diese 5 Fehler solltet ihr laut Studien vermeiden"}]}]}},"_links":{"self":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/8869","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/comments?post=8869"}],"version-history":[{"count":0,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/8869\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media\/8868"}],"wp:attachment":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media?parent=8869"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/categories?post=8869"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/tags?post=8869"},{"taxonomy":"company","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/companies?post=8869"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/products?post=8869"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}