CVE-2025-46560
published 2025-04-30CVE-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…
PriorityP342high7.5CVSS 3.1
AVNACLPRNUINSUCNINAH
EPSS
0.43%
34.1th percentile
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., , ) 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.
Affected
3 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| vllm-project | vllm | — | — |
| vllm | vllm | >= 0.8.0 < 0.8.5 | 0.8.5 |
| vllm | vllm | >= 0.8.0 < 0.8.5 | 0.8.5 |
CVSS provenance
nvdv3.17.5HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
vendor_redhat6.5MEDIUM
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
OSV
phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
osv·2025-04-29
CVE-2025-46560 [MEDIUM] phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
### Summary
A critical performance vulnerability has been identified in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., , ) 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.
### Details
Affected Component: input_processor_for_phi4mm function.
https://github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744f4e/vllm/model_executor/models/phi4mm.py#L1182-L1197
The code modifies the input_ids list in-place using input_i
GHSA
phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
ghsa·2025-04-29
CVE-2025-46560 [MEDIUM] CWE-1333 phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
### Summary
A critical performance vulnerability has been identified in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., , ) 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.
### Details
Affected Component: input_processor_for_phi4mm function.
https://github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744f4e/vllm/model_executor/models/phi4mm.py#L1182-L1197
The code modifies the input_ids list in-place using input_i
Red Hat
vllm: vLLM phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
vendor_redhat·2025-04-30·CVSS 6.5
CVE-2025-46560 [MEDIUM] CWE-1333 vllm: vLLM phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
vllm: vLLM phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
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., , ) 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.
A flaw was found in the vllm component. The affected versions of vllm have a performance v
No detection rules found.
No public exploits indexed.
No writeups or analysis indexed.
2025-04-30
Published