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
Affected Vendors & Products
References
History
Mon, 06 Jul 2026 20:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Vllm-project
Vllm-project vllm |
|
| Vendors & Products |
Vllm-project
Vllm-project vllm |
Mon, 06 Jul 2026 20:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
ssvc
|
Mon, 06 Jul 2026 19:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | vLLM speech-to-text endpoints allocate full upload before enforcing the audio file-size limit | |
| Weaknesses | CWE-400 CWE-770 |
|
| References |
| |
| Metrics |
cvssV3_1
|
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-07-06T19:49:44.773Z
Reserved: 2026-06-16T23:52:12.058Z
Link: CVE-2026-55646
Updated: 2026-07-06T19:49:27.923Z
No data.
No data.
OpenCVE Enrichment
Updated: 2026-07-06T20:30:05Z