- Description
- vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to inefficient list concatenation operations, the algorithm exhibits quadratic time complexity (O(n²)), allowing malicious actors to trigger resource exhaustion via specially crafted inputs. This issue has been patched in version 0.8.5.
- Source
- security-advisories@github.com
- NVD status
- Analyzed
CVSS 3.1
- Type
- Primary
- Base score
- 7.5
- Impact score
- 3.6
- Exploitability score
- 3.9
- Vector string
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Severity
- HIGH
- security-advisories@github.com
- CWE-1333
- Hype score
- Not currently trending
CVE-2025-46560 - Interesting 🤔vLLM DoS vulnerability due to quadratic time complexity in multimodal tokenizer input preprocessing. Inefficient list concatenation lets attackers craft inputs with many placeholders (e.g., <|audio_1|>), causing CPU/memory exhaustion. ️
@gothburz
30 Apr 2025
7 Impressions
0 Retweets
0 Likes
0 Bookmarks
0 Replies
0 Quotes
CVE-2025-46560 vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical perfo… https://t.co/PwKYft5b0i
@CVEnew
30 Apr 2025
568 Impressions
0 Retweets
0 Likes
0 Bookmarks
1 Reply
0 Quotes
[
{
"nodes": [
{
"negate": false,
"cpeMatch": [
{
"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"vulnerable": true,
"matchCriteriaId": "19C6D0C7-632B-4AA7-97E5-CCF21EC350E5",
"versionEndExcluding": "0.8.5",
"versionStartIncluding": "0.8.0"
}
],
"operator": "OR"
}
]
}
]