CVE-2026-55646

CVE-2026-55646 (vLLM) affects vLLM versions 0.22.0–0.23.0. The routes /v1/audio/transcriptions and /v1/audio/translations call request.file.read() to fully materialize an uploaded audio file before enforcing the documented size limit (default 25 MB). This can cause the server to allocate memory p...

CVE-2026-55646 vLLM speech-to-text endpoints allocate full upload before enforcing the audio file-size limit

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 VLLMMAXAUDIOCLIPFILESIZEMB...

GHSA-6PR9-RP53-2PMC vLLM: OOM Denial of Service via Audio Decompression Bomb

Summary vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to 14.9GB of float32 PCM at decode time. Tested on vLLM v0.19.0. Details SpeechToTextProcessor rejects uploads over VLLMMAXAUDIOCLIPFILESIZEMB default 25MB based on...

CVE-2026-34760

vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing tomono, while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results...