PT-2026-55978 · Vllm · Vllm

Rexpository · Published 2026-07-06 · Updated 2026-07-06 · CVE-2026-55646

NVD

CVSS v3.1

6.5

Medium

Base vector

AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

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.

Exploit

Fix

Allocation of Resources Without Limits

Resource Exhaustion

Weakness Enumeration

CWE-770

CWE-400

Related Identifiers

CVE-2026-55646

Affected Products

Vllm

References · 4

• 🔥 https://github.com/vllm-project/vllm/security/advisories/GHSA-v82g-2437-67m2 · Exploit
• https://nvd.nist.gov/vuln/detail/CVE-2026-55646 · Security Note
• https://github.com/vllm-project/vllm/commit/b997071ec493765abbed990c65843ed05e4708a8 · Note
• https://github.com/vllm-project/vllm/pull/45510 · Note