CVE-2026-53923— vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow
Get alerts for future matching vulnerabilitiesLog in to subscribe
I. Basic Information for CVE-2026-53923
Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗ Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
Vulnerability Title
vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow
Source: NVD (National Vulnerability Database)
Vulnerability Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0.
Source: NVD (National Vulnerability Database)
CVSS Information
N/A
Source: NVD (National Vulnerability Database)
Vulnerability Type
数值类型间的不正确转换
Source: NVD (National Vulnerability Database)
Affected Products
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| vllm-project | vllm | >= 0.5.5, < 0.23.1rc0 | - |
II. Public POCs for CVE-2026-53923
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POCPremium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2026-53923
请登录查看更多情报信息。
Other References for CVE-2026-53923 (3)
Same Patch Batch · vllm-project · 2026-06-22 · 8 CVEs total
| CVE-2026-48746 | 9.1 CRITICAL | vLLM: OpenAI auth bypass |
| CVE-2026-54232 | 8.8 HIGH | vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile |
| CVE-2026-41523 | 7.5 HIGH | vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arb |
| CVE-2026-47155 | 6.5 MEDIUM | vLLM: Artifact Pin Decay in vLLM allows pinned deployments to load unpinned code, weights, |
| CVE-2026-54233 | 6.5 MEDIUM | vLLM: OOM Denial of Service via Audio Decompression Bomb |
| CVE-2026-54236 | 5.3 MEDIUM | vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router |
| CVE-2026-54235 | vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kern |
IV. Related Vulnerabilities
Same product: vllm
- CVE-2026-47155
vLLM: Artifact Pin Decay in vLLM allows pinned deployments t - CVE-2026-41523
vLLM: Security Check Bypass via assert Statement in Activati - CVE-2026-54232
vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile - CVE-2026-54233
vLLM: OOM Denial of Service via Audio Decompression Bomb - CVE-2026-54236
vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses
Same vendor: vllm-project
- CVE-2026-47155
vLLM: Artifact Pin Decay in vLLM allows pinned deployments t - CVE-2026-41523
vLLM: Security Check Bypass via assert Statement in Activati - CVE-2026-54232
vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile - CVE-2026-54233
vLLM: OOM Denial of Service via Audio Decompression Bomb - CVE-2026-54236
vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses
Same weakness: CWE-681
- CVE-2026-9143
Incorrect Conversion between Numeric Types in NI grpc-device - CVE-2026-24192
NVIDIA Display Driver 安全漏洞 - CVE-2026-26178
Windows Advanced Rasterization Platform Elevation of Privile - CVE-2026-34945
Wasmtime leaks host data with 64-bit tables and Winch - CVE-2026-24174
NVIDIA Triton Inference Server 安全漏洞
V. Comments for CVE-2026-53923
No comments yet