CVE-2026-115916 (GCVE-0-2026-115916)
Vulnerability from cvelistv5 – Published: 2026-10-26 17:18 – Updated: 2026-11-02 17:50
VLAI
EPSS
VEX
Title
vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
Summary
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0.
Severity
6.5 (Medium)
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-11-02 17:49 UTC
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/vllm-project/vllm/security/adv… | x_refsource_CONFIRM |
| https://github.com/vllm-project/vllm/pull/59491 | x_refsource_MISC |
| https://github.com/vllm-project/vllm/commit/37cec… | x_refsource_MISC |
| https://github.com/vllm-project/vllm/releases/tag… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| vllm-project | vllm |
Affected:
< 0.32.0
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-115916",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-02T17:49:45.650631Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-11-02T17:50:28.478Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "vllm",
"vendor": "vllm-project",
"versions": [
{
"status": "affected",
"version": "\u003c 0.32.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0."
}
],
"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-129",
"description": "CWE-129: Improper Validation of Array Index",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-193",
"description": "CWE-193: Off-by-one Error",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-10-26T17:18:17.582Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4"
},
{
"name": "https://github.com/vllm-project/vllm/pull/59491",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/pull/59491"
},
{
"name": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229"
},
{
"name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
}
],
"source": {
"advisory": "GHSA-q97c-p368-75c4",
"discovery": "UNKNOWN"
},
"title": "vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-115916",
"datePublished": "2026-10-26T17:18:17.582Z",
"dateReserved": "2026-10-23T20:21:45.107Z",
"dateUpdated": "2026-11-02T17:50:28.478Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-115916",
"date": "2026-11-16",
"epss": "0.00312",
"percentile": "0.24417"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"product": "vllm",
"vendor": "vllm-project",
"versions": [
{
"status": "affected",
"version": "\u003c 0.32.0"
}
]
}
],
"source": "security-advisories@github.com"
}
],
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"matchCriteriaId": "F7BDDF1C-9078-4F18-A972-846C4C1363E5",
"versionEndExcluding": "0.32.0",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0."
}
],
"id": "CVE-2026-115916",
"lastModified": "2026-11-02T18:18:39.033",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"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"
},
"exploitabilityScore": 2.8,
"impactScore": 3.6,
"source": "security-advisories@github.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-115916",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-02T17:49:45.650631Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-10-26T18:17:39.080",
"references": [
{
"source": "security-advisories@github.com",
"tags": [
"Patch"
],
"url": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229"
},
{
"source": "security-advisories@github.com",
"tags": [
"Patch"
],
"url": "https://github.com/vllm-project/vllm/pull/59491"
},
{
"source": "security-advisories@github.com",
"tags": [
"Release Notes"
],
"url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
},
{
"source": "security-advisories@github.com",
"tags": [
"Patch",
"Vendor Advisory"
],
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4"
}
],
"sourceIdentifier": "security-advisories@github.com",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-129"
},
{
"lang": "en",
"value": "CWE-193"
}
],
"source": "security-advisories@github.com",
"type": "Secondary"
}
]
}
},
"redhat_vex": {
"aggregate_severity": "Moderate",
"current_release_date": "2026-10-30T07:08:28+00:00",
"cve": "CVE-2026-115916",
"id": "CVE-2026-115916",
"initial_release_date": "2026-10-26T17:18:17.582000+00:00",
"product_status:known_affected": "31",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "vllm: vLLM: Denial of Service via out-of-bounds prompt token ID",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-115916.json",
"version": "3"
},
"suse_vex": {
"aggregate_severity": "moderate",
"current_release_date": "2026-10-28T00:46:53Z",
"cve": "CVE-2026-115916",
"id": "CVE-2026-115916",
"initial_release_date": "2026-10-28T00:46:53Z",
"source": "SUSE CSAF VEX",
"status": "interim",
"title": "SUSE CVE CVE-2026-115916",
"url": "https://ftp.suse.com/pub/projects/security/csaf-vex/2026/cve-2026-115916.json",
"version": "2"
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-115916",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-02T17:49:45.650631Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-11-02T17:49:57.747Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "vllm",
"vendor": "vllm-project",
"versions": [
{
"status": "affected",
"version": "\u003c 0.32.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0."
}
],
"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-129",
"description": "CWE-129: Improper Validation of Array Index",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-193",
"description": "CWE-193: Off-by-one Error",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-10-26T17:18:17.582Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4"
},
{
"name": "https://github.com/vllm-project/vllm/pull/59491",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/pull/59491"
},
{
"name": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229"
},
{
"name": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
}
],
"source": {
"advisory": "GHSA-q97c-p368-75c4",
"discovery": "UNKNOWN"
},
"title": "vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-115916",
"datePublished": "2026-10-26T17:18:17.582Z",
"dateReserved": "2026-10-23T20:21:45.107Z",
"dateUpdated": "2026-11-02T17:50:28.478Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Loading…
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.
Loading…