SOC status:Duty analyst on shift

UK Cyber Defence
VulnerabilityAnalyzed

CVE-2026-55646

vLLM is an inference and serving engine for large language models.

MEDIUM 6.5EPSS 0.52%

Does this matter?

Lower severity and a low EPSS score (0.52%). Track it; it rarely justifies an emergency change on its own.

Description

vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed upload size limit (default 25 MB) later in the speech-to-text preprocessing step, so an API caller who can reach those routes can submit an oversized multipart upload and cause vLLM to allocate memory proportional to the uploaded file size before the request is rejected as too large, creating memory pressure or terminating the process depending on deployment resource limits. This issue is fixed in version 0.24.0.

CVSS 3.1
6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS
0.52% probability · 43th percentile
CISA KEV
Not listed
Weakness
CWE-400, CWE-770
Affected
vllm/vllm
Source
security-advisories@github.com

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.