CVE-2026-55646 Details
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.
A denial-of-service vulnerability has been identified in vLLM, an inference and serving engine for large language models, specifically in versions 0.22.0 prior to 0.23.0. The issue arises in the '/v1/audio/transcriptions' and '/v1/audio/translations' routes, where the application reads the entire uploaded audio file into memory before validating its size against the documented limit of 25 MB. This flaw allows an API caller to upload oversized files, causing vLLM to allocate memory based on the file size. The request is only rejected after the file has been fully processed, leading to potential memory pressure or process termination, depending on the deployment's resource limits.
Users can update to vLLM version 0.24.0 or later, where this vulnerability has been fixed. For those unable to upgrade, consider implementing a reverse proxy or ASGI layer that enforces body-size limits before the request reaches vLLM.
Metrics
CVSS 4.0 Severity and Vector Strings:
No CVSS 4.0 data is available for this CVE.
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
CISA-ADP
Assessed Jul 6, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://github.com/vllm-project/vllm/security/advisories/GHSA-v82g-2437-67m2 | CISA-ADP | Vendor Advisory |
| https://github.com/vllm-project/vllm/commit/b997071ec493765abbed990c65843ed05e4708a8 | [email protected] | Patch |
| https://github.com/vllm-project/vllm/pull/45510 | [email protected] | Issue TrackingPatch |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-v82g-2437-67m2 | [email protected] | Vendor Advisory |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-400 | Uncontrolled Resource Consumption | [email protected] |
| CWE-770 | Allocation of Resources Without Limits or Throttling | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| vllm vllm | >= 0.22.0, < 0.24.0 |
CPE
Remediation
| |
Change History
3 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Jul 7, 2026 | Initial Analysis | [email protected] |
| Jul 6, 2026 | CVE Modified | CISA-ADP |
| Jul 6, 2026 | New CVE Received | [email protected] |