CVE-2026-55646

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.

How to fix CVE-2026-55646

To remediate CVE-2026-55646, upgrade the affected package to a fixed version below.

• —upgrade to 0.24.0 or later

Is CVE-2026-55646 being exploited?

Low — EPSS is 0.3%, meaning exploitation activity has not been observed at scale.

Affected packages (1)

• >= 0.22.0, < 0.24.0

CVSS scores

References (6)

• ADVISORYnvd.nist.gov/vuln/detail/CVE-2026-55646
• PATCHgithub.com/vllm-project/vllm
• WEBgithub.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2305.yaml
• WEBgithub.com/vllm-project/vllm/commit/b997071ec493765abbed990c65843ed05e4708a8