{"id":"CVE-2026-34756","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 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the…","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","CWE-1284"],"vendor":"vllm","product":"vllm","affected":["vllm >= 0.1.0, < 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-2026-34756","references":[{"url":"https://github.com/vllm-project/vllm/commit/b111f8a61f100fdca08706f41f29ef3548de7380","label":"security-advisories@github.com"},{"url":"https://github.com/vllm-project/vllm/pull/37952","label":"security-advisories@github.com"},{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-3mwp-wvh9-7528","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-2026-34756","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2455425","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34756.json","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-34756"},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2298.yaml"},{"url":"https://github.com/vllm-project/vllm"}],"tags":["nvd","osv","pip"],"epss":0.00421,"epssPercentile":0.36101,"ingestedAt":"2026-07-07T12:52:59.582Z","aliases":["GHSA-3mwp-wvh9-7528","PYSEC-2026-2298"],"ecosystem":"pip","slug":"CVE-2026-34756","body":"## Overview\n\nvLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue. This vulnerability is fixed in 0.19.0.\n\n## Affected\n\n- `vllm >= 0.1.0, < 0.19.0`\n\n## Remediation\n\nUpgrade past the affected range:\n\n- `vllm 0.19.0`\n\n## Package advisory (CVE-2026-34756)\n\nAffected packages:\n\n- `vllm >= 0.1.0, < 0.19.0`\n\nPatched in:\n\n- `vllm 0.19.0`\n\nSource: https://osv.dev/vulnerability/GHSA-3mwp-wvh9-7528","depth":"sunlit","depthScore":36,"depthScoreParts":{"impact":35.8,"likelihood":0.1,"exploitation":0,"ransomware":0},"changes":[]}