vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`
vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.
- Products
- Not specified
- Affected versions
- Not specified
- Fixed versions
- Not specified
- CVEs
- CVE-2025-62426
- Confirmed fixed CVEs
- Not specified
- Updated in this feed
- 4 Nov 2026, 22:55 UTC · Revision 1
Source evidence
vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`
core-osv · Original sourcePublished 21 Nov 2025, 01:21 UTC
vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.
osv:CVE-2025-62426
Complete source record
{
"id": "462a3de64014e2b8f5bbc525ca200b3549a0a17c317771de53eb7c86fb3156c8",
"url": "https://osv.dev/vulnerability/CVE-2025-62426",
"method": "structured",
"payload": {
"kind": "advisory",
"title": "vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`",
"summary": "vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.",
"evidence": "osv:CVE-2025-62426",
"products": [],
"severity": "medium",
"structured": {
"id": "CVE-2025-62426",
"aliases": [
"CVE-2025-62426",
"GHSA-69j4-grxj-j64p",
"PYSEC-2026-2012"
],
"metrics": [
{
"type": "CVSS_V3",
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H"
}
],
"affected": [
{
"ranges": [
{
"repo": "https://github.com/vllm-project/vllm",
"type": "GIT",
"events": [
{
"introduced": "09c7792610ada9f88bbf87d32b472dd44bf23cc2"
},
{
"fixed": "439368496db48d8f992ba8c606a0c0b1eebbfa69"
},
{
"introduced": "b761df963c2032144468a99bcb39a11e73e16ca4"
},
{
"fixed": "3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b"
}
],
"database_specific": {
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0.5.5"
},
{
"fixed": "0.11.1"
}
],
"source": "CPE_RANGE"
},
{
"cpe": "cpe:2.3:a:vllm:vllm:0.11.1:rc0:*:*:*:*:*:*",
"range": [
{
"introduced": "0.11.1-rc0"
},
{
"last_affected": "0.11.1-rc0"
}
],
"source": "CPE_STRING"
},
{
"cpe": "cpe:2.3:a:vllm:vllm:0.11.1:rc1:*:*:*:*:*:*",
"range": [
{
"introduced": "0.11.1-rc1"
},
{
"last_affected": "0.11.1-rc1"
}
],
"source": "CPE_STRING"
},
{
"range": [
{
"fixed": "3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b"
}
],
"source": "REFERENCES_COMMIT"
}
]
}
}
],
"versions": [
"0.11.1-rc0",
"0.11.1-rc1",
"v0.11.1rc1",
"v0.11.1rc0",
"v0.11.0rc1"
],
"database_specific": {
"source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2025-62426.json"
}
}
],
"modified": "2026-10-28T02:30:40.139382315Z",
"provider": "osv",
"references": [
"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610",
"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814",
"https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/62xxx/CVE-2025-62426.json",
"https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p",
"https://nvd.nist.gov/vuln/detail/CVE-2025-62426",
"https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b",
"https://github.com/vllm-project/vllm/pull/27205"
],
"provider_metadata": {
"cwe_ids": [
"CWE-770"
],
"cna_assigner": "GitHub_M",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/62xxx/CVE-2025-62426.json"
}
},
"related_cves": [
{
"value": "CVE-2025-62426",
"evidence": "/id"
}
],
"security_relevant": true,
"severity_evidence": "/severity/0/score"
},
"source_id": "core-osv",
"document_id": 507766,
"published_at": "2025-11-21T01:21:29.546+00:00"
}