CVE Feed

    Dashboard / CVE / CVE-2026-34755

    CVE-2026-34755

    vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0.

    Published:Apr 6, 2026
    Last Modified:Aug 25, 2026
    EPS:Apr 6, 2026
    EPSS Score:0.00464
    CVSS Score:6.5

    Affected Products

    Vendor
    Vllm
    Product
    Vllm
    Vendor
    Vllm-project
    Product
    Vllm

    Exploits

    No exploit reference

    Related CVEs

    CVE-2026-78684 (CVSS 6.9) — vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in…
    CVE-2026-41523 (CVSS 7.5) — vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based sec…
    CVE-2026-48746 (CVSS 9.1) — vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerabi…
    CVE-2026-56340 (CVSS 8.7) — vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing.…
    CVE-2025-71379 (CVSS 5.3) — vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabiliti…
    CVE-2026-5497 (CVSS 7.5) — vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to u…
    CVE-2026-44223 (CVSS 6.5) — vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the ex…
    CVE-2026-44222 (CVSS 6.5) — vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there i…
    CVE-2026-7141 (CVSS 2.9) — A vulnerability was found in vLLM up to 0.19.0. The affected element is the function has_mamba_layers of the f…
    CVE-2026-34756 (CVSS 6.5) — vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denia…

    Common Vulnerability Scoring System

    Attack Vector
    Network
    Adjacent
    Local
    Physical
    Privileges Required
    None
    Low
    High
    User Interaction
    None
    Required
    Scope
    Unchanged
    Changed
    Confidentiality
    None
    Low
    High
    Integrity
    None
    Low
    High
    Availability
    None
    Low
    High