CVE-2026-69147 (GCVE-0-2026-69147)
Vulnerability from cvelistv5
Published
2026-09-16 17:49
Modified
2026-09-16 18:37
Severity ?
VLAI Severity ?
EPSS score ?
CWE
Summary
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine's _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine's KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0.
References
| URL | Tags | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| vllm-project | vllm |
Version: < 0.28.0 |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-69147",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-16T18:37:08.090589Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-16T18:37:14.118Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "vllm",
"vendor": "vllm-project",
"versions": [
{
"status": "affected",
"version": "\u003c 0.28.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine\u0027s _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine\u0027s KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0."
}
],
"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-400",
"description": "CWE-400: Uncontrolled Resource Consumption",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-770",
"description": "CWE-770: Allocation of Resources Without Limits or Throttling",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-16T17:49:20.427Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j"
},
{
"name": "https://github.com/vllm-project/vllm/pull/47259",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/pull/47259"
},
{
"name": "https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda"
},
{
"name": "https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d"
}
],
"source": {
"advisory": "GHSA-8pw2-6jv3-mj5j",
"discovery": "UNKNOWN"
},
"title": "vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-69147",
"datePublished": "2026-09-16T17:49:20.427Z",
"dateReserved": "2026-08-03T15:20:30.218Z",
"dateUpdated": "2026-09-16T18:37:14.118Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"vulnrichment": {
"containers": "{\"cna\": {\"title\": \"vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation\", \"problemTypes\": [{\"descriptions\": [{\"cweId\": \"CWE-400\", \"lang\": \"en\", \"description\": \"CWE-400: Uncontrolled Resource Consumption\", \"type\": \"CWE\"}]}, {\"descriptions\": [{\"cweId\": \"CWE-770\", \"lang\": \"en\", \"description\": \"CWE-770: Allocation of Resources Without Limits or Throttling\", \"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-8pw2-6jv3-mj5j\", \"tags\": [\"x_refsource_CONFIRM\"], \"url\": \"https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j\"}, {\"name\": \"https://github.com/vllm-project/vllm/pull/47259\", \"tags\": [\"x_refsource_MISC\"], \"url\": \"https://github.com/vllm-project/vllm/pull/47259\"}, {\"name\": \"https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda\", \"tags\": [\"x_refsource_MISC\"], \"url\": \"https://github.com/vllm-project/vllm/commit/283893c72292ede38d277e3cd2b9b64c3e4f1dda\"}, {\"name\": \"https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d\", \"tags\": [\"x_refsource_MISC\"], \"url\": \"https://github.com/vllm-project/vllm/commit/ba22152096b2484faa3579624a253d54804d876d\"}], \"affected\": [{\"vendor\": \"vllm-project\", \"product\": \"vllm\", \"versions\": [{\"version\": \"\u003c 0.28.0\", \"status\": \"affected\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-09-16T17:49:20.427Z\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine\u0027s _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine\u0027s KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0.\"}], \"source\": {\"advisory\": \"GHSA-8pw2-6jv3-mj5j\", \"discovery\": \"UNKNOWN\"}}, \"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-69147\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-09-16T18:37:08.090589Z\"}}}], \"references\": [{\"url\": \"https://github.com/vllm-project/vllm/security/advisories/GHSA-8pw2-6jv3-mj5j\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-09-16T18:36:52.431Z\"}}]}",
"cveMetadata": "{\"cveId\": \"CVE-2026-69147\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"state\": \"PUBLISHED\", \"assignerShortName\": \"GitHub_M\", \"dateReserved\": \"2026-08-03T15:20:30.218Z\", \"datePublished\": \"2026-09-16T17:49:20.427Z\", \"dateUpdated\": \"2026-09-16T18:37:14.118Z\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Sightings
| Author | Source | Type | Date |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
- Confirmed: The vulnerability is confirmed from an analyst perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
- Patched: This vulnerability was successfully patched by the user reporting the sighting.
- Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
- Not confirmed: The user expresses doubt about the veracity of the vulnerability.
- Not patched: This vulnerability was not successfully patched by the user reporting the sighting.
Loading…
Loading…