{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-44223","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","state":"PUBLISHED","assignerShortName":"GitHub_M","dateReserved":"2026-05-05T15:42:40.518Z","datePublished":"2026-05-12T19:58:40.862Z","dateUpdated":"2026-05-12T19:58:40.862Z"},"containers":{"cna":{"title":"vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters","problemTypes":[{"descriptions":[{"cweId":"CWE-131","lang":"en","description":"CWE-131: Incorrect Calculation of Buffer Size","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-704","lang":"en","description":"CWE-704: Incorrect Type Conversion or Cast","type":"CWE"}]}],"metrics":[{"cvssV3_1":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"HIGH","baseScore":6.5,"baseSeverity":"MEDIUM","confidentialityImpact":"NONE","integrityImpact":"NONE","privilegesRequired":"LOW","scope":"UNCHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","version":"3.1"}}],"references":[{"name":"https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw","tags":["x_refsource_CONFIRM"],"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw"},{"name":"https://github.com/vllm-project/vllm/pull/38610","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/pull/38610"}],"affected":[{"vendor":"vllm-project","product":"vllm","versions":[{"version":">= 0.18.0, < 0.20.0","status":"affected"}]}],"providerMetadata":{"orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M","dateUpdated":"2026-05-12T19:58:40.862Z"},"descriptions":[{"lang":"en","value":"vLLM is an inference and serving engine for large language models (LLMs). From  to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., \"repetition_penalty\": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0."}],"source":{"advisory":"GHSA-83vm-p52w-f9pw","discovery":"UNKNOWN"}}}}