Medium [CVE-2026-55646] Denial of Service due to excessive memory allocation via oversized audio file uploads

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. This occurs before the configured file size limit is checked, leading to memory pressure or process termination, resulting in a Denial of Service (DoS).

This Moderate denial of service flaw in vLLM, which could lead to excessive memory allocation when processing oversized audio files, does not affect Red Hat products. The vulnerable code is not present in Red Hat's supported offerings.

Red Hat severity: Moderate — CVSS 6.5 (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H). Weakness: CWE-770.

Red Hat lists Red Hat AI Inference Server; Red Hat Enterprise Linux AI (RHEL AI) 3; Red Hat OpenShift AI (RHOAI) as not affected.