vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving
CVE-2026-53923 · GHSA-5jv2-g5wq-cmr4 · published 2026-06-17 · updated 2026-07-17
- Severity
- Medium
- CVSS score
- 7.5
- Chance of exploitation (EPSS)
- 0.48%
- Fixed in
- 0.24.0
- Exploitation No known exploitation
- Automatable No
- Technical impact Partial
- CISA SSVC
vLLM is designed for multi-tenant inference serving. GPU memory is reused across requests from different users. When the dequantize kernel partially fills an output tensor: 1. The output tensor DW is allocated with torch::empty -- the buffer contains whatever was previously in that GPU memory region 2. The dequantize kernel fills only a truncated portion of the buffer 3. The unfilled portion retains residual data from prior GPU operations, which may include tensor data from other users' inference requests 4. The contaminated tensor proceeds through the model computation 5. No error or warning is generated -- the partial fill is silent This is a confidentiality violation.
Upgrade vllm to 0.24.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
A fix for this vulnerability was added here: https://github.com/vllm-project/vllm/pull/44971
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | >= 0.5.5, < 0.24.0 | 0.24.0 |
- CriticalPhoenix: Format String Injection in applyChatTemplatearize-phoenix
- CriticalFlowise: Unauthenticated OAuth2 token refresh endpoint returns access tokens — enables token theft for any connected serviceflowise
- CriticalMLflow: Environment variable injection in AI Gateway secrets enables server-side credential exfiltrationmlflow
- HighConfig revision hashes could expose password verifiersopenclaw
- Highn8n: Shared Credential Header Leak via HTTP Request Pagination Expressionn8n, n8n, n8n
- HighWorkspace dotenv files could override provider credentialsopenclaw
- CriticalvLLM: OpenAI auth bypassvllm
- CriticalvLLM has RCE In Video Processingvllm
- CriticalvLLM Allows Remote Code Execution via PyNcclPipe Communication Servicevllm
- CriticalvLLM Vulnerable to Remote Code Execution via Mooncake Integrationvllm
- CriticalCVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0vllm
- CriticalvLLM Deserialization of Untrusted Data vulnerabilityvllm
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.