CVE-2026-57173 vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
Unauthenticated attackers can crash vLLM workers by sending small compressed audio inputs that cause excessive memory allocation.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-57173?
CVE-2026-57173 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 16 Sep 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder. An unauthenticated client can therefore submit a small compressed audio input that expands into a very large float32 PCM allocation, bypassing the duration guard already used by /v1/audio/transcriptions and causing an out-of-memory worker crash. Inline data URLs reach this path without being bounded by VLLM_AUDIO_FETCH_TIMEOUT. The issue affects deployments serving an audio-capable model, and authentication changes only the deployment-specific reachability. This issue is fixed in version 0.24.0.
Weakness: CWE-770
Which versions are affected by CVE-2026-57173?
3 open source packages ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | All versions | 0.24.0 |
vllm PyPI | All versions | 0.24.0 |
vllm PyPI | All versions | 0.24.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-57173?
Upgrade vllm to 0.24.0 or later.
Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.
Is CVE-2026-57173 being exploited?
There is no known exploitation of CVE-2026-57173 in the wild and no public exploit code.
Other vulnerabilities in Vllm Vllm
- CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration
- CVE-2026-22778 vLLM leaks a heap address when PIL throws an error
- CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
- CVE-2024-11041 Remote Code Execution in vllm-project/vllm
- CVE-2026-48746 vLLM: OpenAI auth bypass
Sources
Also known as GHSA-hcwq-8wjf-3gcr, MINI-2mgx-c97m-5vw2, MINI-8w89-pg8g-gxhp, MINI-h739-jxf4-8r39, PYSEC-2026-4179.