vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, 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. This vulnerability is fixed in 0.23.1rc0.

Affected: PyPI: vllm

### 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 `VLLM_MAX_AUDIO_CLIP_FILESIZE_MB` (default 25MB) based on compressed byte length, but the audio decoder in `audio.py` accumulates all decoded frames into memory with no size limit before returning:

```python # speech_to_text.py L184-189 if len(audio_data) / 1024 ** 2 > self.max_audio_filesize_mb: raise VLLMValidationError(...) y, sr = load_audio(buf, sr=self.asr_config.sample_rate) # decoded size unchecked

# audio.py L77-107 chunks: list[npt.NDArray] = [] for frame in container.decode(stream): chunks.append(frame.to_ndarray()) audio = np.concatenate(chunks, axis=-1).astype(np.float32) # single contiguous allocation ```

A 25MB OPUS file at 6kbps encodes ~8.7 hours of audio. Decoding produces ~5.7GB of float32 PCM (232x amplification), and `np.concatenate` then allocates a second contiguous array, bringing peak RSS to ~14.9GB from a single request. `SpeechToTextConfig.max_audio_clip_s` (default 30s) applies only after the full decode and does not prevent the allocation.

### Impact An unauthenticated attacker can exhaust server memory with a small number of concurrent requests, each a valid upload within the documented size limit. Severity was assessed with reference to prior OOM vulnerability reports in vL…

Affected: PyPI: vllm

### 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 `VLLM_MAX_AUDIO_CLIP_FILESIZE_MB` (default 25MB) based on compressed byte length, but the audio decoder in `audio.py` accumulates all decoded frames into memory with no size limit before returning:

```python # speech_to_text.py L184-189 if len(audio_data) / 1024 ** 2 > self.max_audio_filesize_mb: raise VLLMValidationError(...) y, sr = load_audio(buf, sr=self.asr_config.sample_rate) # decoded size unchecked

# audio.py L77-107 chunks: list[npt.NDArray] = [] for frame in container.decode(stream): chunks.append(frame.to_ndarray()) audio = np.concatenate(chunks, axis=-1).astype(np.float32) # single contiguous allocation ```

A 25MB OPUS file at 6kbps encodes ~8.7 hours of audio. Decoding produces ~5.7GB of float32 PCM (232x amplification), and `np.concatenate` then allocates a second contiguous array, bringing peak RSS to ~14.9GB from a single request. `SpeechToTextConfig.max_audio_clip_s` (default 30s) applies only after the full decode and does not prevent the allocation.

### Impact An unauthenticated attacker can exhaust server memory with a small number of concurrent requests, each a valid upload within the documented size limit. Severity was assessed with reference to prior OOM vulnerability reports in vL…

Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Sicherheitsmaßnahmen zu umgehen, einen Denial-of-Service-Zustand zu verursachen, Daten zu manipulieren oder vertrauliche Informationen offenzulegen.