{"id":"CVE-2026-34755","title":"vLLM is an inference and serving engine for large language models (LLMs)","summary":"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 JPE…","severity":"medium","cvss":6.5,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","cwe":["CWE-770"],"vendor":"vllm","product":"vllm","affected":["vllm >= 0.7.0, < 0.19.0"],"patched":["vllm 0.19.0"],"published":"2026-04-06","updated":"2026-07-07","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-34755","references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p","label":"security-advisories@github.com"},{"url":"https://access.redhat.com/errata/RHSA-2026:36005","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/errata/RHSA-2026:36006","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/security/cve/CVE-2026-34755","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2455403","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34755.json","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-34755"},{"url":"https://github.com/vllm-project/vllm/pull/38636"},{"url":"https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395"},{"url":"https://github.com/vllm-project/vllm"},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-144.yaml"},{"url":"https://access.redhat.com/errata/RHSA-2026:59151"},{"url":"https://access.redhat.com/errata/RHSA-2026:59144"},{"url":"https://access.redhat.com/errata/RHSA-2026:57390"},{"url":"https://access.redhat.com/errata/RHSA-2026:57389"},{"url":"https://access.redhat.com/errata/RHSA-2026:57387"},{"url":"https://access.redhat.com/errata/RHSA-2026:57380"}],"tags":["nvd","osv","pip"],"epss":0.00843,"epssPercentile":0.5611,"ingestedAt":"2026-07-07T12:52:59.574Z","aliases":["GHSA-pq5c-rjhq-qp7p","PYSEC-2026-144"],"ecosystem":"pip","slug":"CVE-2026-34755","body":"## Overview\n\nvLLM 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.\n\n## Affected\n\n- `vllm >= 0.7.0, < 0.19.0`\n\n## Remediation\n\nUpgrade past the affected range:\n\n- `vllm 0.19.0`\n\n## Package advisory (CVE-2026-34755)\n\nAffected packages:\n\n- `vllm >= 0.7.0, < 0.19.0`\n\nPatched in:\n\n- `vllm 0.19.0`\n\nSource: https://osv.dev/vulnerability/GHSA-pq5c-rjhq-qp7p","depth":"sunlit","depthScore":36,"depthScoreParts":{"impact":35.8,"likelihood":0.2,"exploitation":0,"ransomware":0},"changes":[]}