{"id":"CVE-2026-44223","state":"PUBLISHED","title":"vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters","description":"vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 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.","publishedAt":"2026-05-12T19:58:40.862Z","updatedAt":"2026-06-22T21:49:24.277Z","severity":{"score":6.5,"label":"Medium","version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","source":"GitHub_M"},"assigner":"GitHub_M","products":["vllm-project vllm"],"affected":[{"vendor":"vllm-project","product":"vllm","versions":[{"version":">= 0.18.0, < 0.20.0","status":"affected"}]}],"references":["https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw","https://github.com/vllm-project/vllm/pull/38610"],"weaknesses":["CWE-131","CWE-704"],"ingestedAt":"2026-10-29T20:11:57.932Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/44xxx/CVE-2026-44223.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-44223","state":"PUBLISHED","datePublished":"2026-05-12T19:58:40.862Z","dateUpdated":"2026-06-22T21:49:24.277Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2026-05-05T15:42:40.518Z"},"containers":{"cna":{"title":"vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters","descriptions":[{"lang":"en","value":"vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 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."}],"affected":[{"vendor":"vllm-project","product":"vllm","versions":[{"version":">= 0.18.0, < 0.20.0","status":"affected"}]}],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw","name":"https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw","tags":["x_refsource_CONFIRM"]},{"url":"https://github.com/vllm-project/vllm/pull/38610","name":"https://github.com/vllm-project/vllm/pull/38610","tags":["x_refsource_MISC"]}],"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"}}],"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"}]}],"providerMetadata":{"shortName":"GitHub_M","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateUpdated":"2026-06-22T21:49:24.277Z"},"source":{"advisory":"GHSA-83vm-p52w-f9pw","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw","tags":["exploit"]},{"url":"https://github.com/vllm-project/vllm/pull/38610","tags":["exploit"]}],"metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-05-15T14:44:05.012494Z","id":"CVE-2026-44223","options":[{"Exploitation":"poc"},{"Automatable":"no"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-05-15T14:46:25.695Z"}}]}}}