{"id":"CVE-2025-62426","aliases":["EUVD-2025-198356","GHSA-69j4-grxj-j64p","PYSEC-2026-2012"],"status":"published","title":"vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`","description":"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.","severity":{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-12","score":0.00538,"percentile":0.45815,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-770"],"published":"2025-11-20T21:26:24Z","modified":"2026-10-28T02:30:40Z","fixes":[{"ecosystem":"PyPI","package":"vllm","fixed_in":["0.11.1"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.5.5"},{"fixed":"0.11.1"}]}]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.5.5"},{"fixed":"0.11.1"}]}],"versions":["0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.5.5"},{"fixed":"0.11.1"}]}],"versions":["0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"]}],"products":[{"vendor":"vllm","product":"vllm"},{"vendor":"vllm-project","product":"vllm"}],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p","tags":["x_refsource_CONFIRM","Vendor Advisory","advisory","web"]},{"url":"https://github.com/vllm-project/vllm/pull/27205","tags":["x_refsource_MISC","Issue Tracking","fix","web"]},{"url":"https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b","tags":["x_refsource_MISC","Patch","fix","web"]},{"url":"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610","tags":["x_refsource_MISC","Product","web"]},{"url":"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814","tags":["x_refsource_MISC","Product","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2025-62426","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-69j4-grxj-j64p","tags":["advisory"]},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2012.yaml","tags":["web"]},{"url":"https://github.com/vllm-project/vllm","tags":["package"]},{"url":"https://pypi.org/project/vllm","tags":["web","package"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/62xxx/CVE-2025-62426.json","tags":["advisory"]}],"sources":{"cve":[{"id":"CVE-2025-62426","title":"vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`","description":"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.","status":"published","published":"2025-11-21T01:21:29.546Z","modified":"2025-11-24T18:12:23.183Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"cna"}],"cwes":["CWE-770"],"updated_at":"2026-11-02T14:32:54.87586Z"}],"euvd":[{"id":"EUVD-2025-198356","description":"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.","status":"published","published":"2025-11-21T01:21:29Z","modified":"2025-11-24T18:12:23Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T19:49:13.187271Z"}],"ghsa":[{"id":"GHSA-69j4-grxj-j64p","title":"vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`","description":"### Summary\nThe /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 \n\n### Details\nIn serving_engine.py, the chat_template_kwargs are unpacked into kwargs passed to chat_utils.py `apply_hf_chat_template` with no validation on the keys or values in that chat_template_kwargs dict. This means they can be used to override optional parameters in the `apply_hf_chat_template` method, such as `tokenize`, changing its default from False to True.\n\nhttps://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814\n\nhttps://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610\n\nBoth serving_chat.py and serving_tokenization.py call into this `_preprocess_chat` method of `serving_engine.py` and they both pass in `chat_template_kwargs`.\n\nSo, a `chat_template_kwargs` like `{\"tokenize\": True}` makes tokenization happen as part of applying the chat template, even though that is not expected. Tokenization is a blocking operation, and with sufficiently large input can block the API server's event loop, which blocks handling of all other requests until this tokenization is complete.\n\nThis optional `tokenize` parameter to `apply_hf_chat_template` does not appear to be used, so one option would be to just hard-code that to always be False instead of allowing it to be optionally overridden by callers. A better option may be to not pass `chat_template_kwargs` as unpacked kwargs but instead as a dict, and only unpack them after the logic in `apply_hf_chat_template` that resolves the kwargs against the chat template.\n\n### Impact\n\nAny authenticated user can cause a denial of service to a vLLM server with Chat Completion or Tokenize requests.\n\n### Fix\n\nhttps://github.com/vllm-project/vllm/pull/27205","status":"published","published":"2025-11-20T21:26:24Z","modified":"2026-07-17T16:15:58Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-770"],"updated_at":"2026-11-02T14:40:44.915484Z"}],"nvd":[{"id":"CVE-2025-62426","description":"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.","status":"published","published":"2025-11-21T02:15:43.57Z","modified":"2026-10-19T13:10:00.11Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"secondary"}],"cwes":["CWE-770"],"updated_at":"2026-11-02T14:11:46.009629Z"}],"osv":[{"id":"CVE-2025-62426","title":"vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`","description":"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.","status":"published","published":"2025-11-21T01:21:29.546Z","modified":"2026-10-28T02:30:40.139382315Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-770"],"updated_at":"2026-11-02T15:44:51.851511Z"},{"id":"GHSA-69j4-grxj-j64p","title":"vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`","description":"### Summary\nThe /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 \n\n### Details\nIn serving_engine.py, the chat_template_kwargs are unpacked into kwargs passed to chat_utils.py `apply_hf_chat_template` with no validation on the keys or values in that chat_template_kwargs dict. This means they can be used to override optional parameters in the `apply_hf_chat_template` method, such as `tokenize`, changing its default from False to True.\n\nhttps://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814\n\nhttps://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610\n\nBoth serving_chat.py and serving_tokenization.py call into this `_preprocess_chat` method of `serving_engine.py` and they both pass in `chat_template_kwargs`.\n\nSo, a `chat_template_kwargs` like `{\"tokenize\": True}` makes tokenization happen as part of applying the chat template, even though that is not expected. Tokenization is a blocking operation, and with sufficiently large input can block the API server's event loop, which blocks handling of all other requests until this tokenization is complete.\n\nThis optional `tokenize` parameter to `apply_hf_chat_template` does not appear to be used, so one option would be to just hard-code that to always be False instead of allowing it to be optionally overridden by callers. A better option may be to not pass `chat_template_kwargs` as unpacked kwargs but instead as a dict, and only unpack them after the logic in `apply_hf_chat_template` that resolves the kwargs against the chat template.\n\n### Impact\n\nAny authenticated user can cause a denial of service to a vLLM server with Chat Completion or Tokenize requests.\n\n### Fix\n\nhttps://github.com/vllm-project/vllm/pull/27205","status":"published","published":"2025-11-20T21:26:24Z","modified":"2026-09-10T03:50:30.637114193Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-770"],"updated_at":"2026-11-02T15:46:39.618611Z"},{"id":"PYSEC-2026-2012","title":"vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`","description":"### Summary\nThe /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 \n\n### Details\nIn serving_engine.py, the chat_template_kwargs are unpacked into kwargs passed to chat_utils.py `apply_hf_chat_template` with no validation on the keys or values in that chat_template_kwargs dict. This means they can be used to override optional parameters in the `apply_hf_chat_template` method, such as `tokenize`, changing its default from False to True.\n\nhttps://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814\n\nhttps://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610\n\nBoth serving_chat.py and serving_tokenization.py call into this `_preprocess_chat` method of `serving_engine.py` and they both pass in `chat_template_kwargs`.\n\nSo, a `chat_template_kwargs` like `{\"tokenize\": True}` makes tokenization happen as part of applying the chat template, even though that is not expected. Tokenization is a blocking operation, and with sufficiently large input can block the API server's event loop, which blocks handling of all other requests until this tokenization is complete.\n\nThis optional `tokenize` parameter to `apply_hf_chat_template` does not appear to be used, so one option would be to just hard-code that to always be False instead of allowing it to be optionally overridden by callers. A better option may be to not pass `chat_template_kwargs` as unpacked kwargs but instead as a dict, and only unpack them after the logic in `apply_hf_chat_template` that resolves the kwargs against the chat template.\n\n### Impact\n\nAny authenticated user can cause a denial of service to a vLLM server with Chat Completion or Tokenize requests.\n\n### Fix\n\nhttps://github.com/vllm-project/vllm/pull/27205","status":"published","published":"2026-07-07T16:03:10.753049Z","modified":"2026-07-07T17:47:19.712741583Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T15:52:55.537808Z"}]}}