CVE-2026-55646

MEDIUMCVSS 6.5/10EPSS 0.29%

Last modified

CVE-2026-55646 is a medium-severity vulnerability rated 6.5/10 on the CVSS scale. 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. EPSS estimates a 0.29% chance of exploitation in the next 30 days.

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.

Metrics

CVSS 3.1
6.5/10

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS Probability
0.29%

21.3th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

VendorProductVersions
VllmVllm>= 0.22.0, < 0.24.0

References

Timeline

Published
Last Modified
Status
Analyzed

Frequently Asked Questions

What is CVE-2026-55646?
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 severe is CVE-2026-55646?
CVE-2026-55646 has a CVSS score of 6.5/10 (MEDIUM severity). The EPSS model estimates a 0.29% probability of exploitation in the next 30 days.
How do I fix CVE-2026-55646?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2026

Are you affected by CVE-2026-55646?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST