Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD 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.
Priority
LOW
Exploitation
NONE
PoC
NONE
Patch
AVAILABLE
Momentum
STABLE
If you run products in this scope, you should treat this CVE as relevant to your environment.
| Date | Total | Labels |
|---|
| 2026-06-22 | 2 | Disclosure1General1 |
| 2026-06-30 | 1 | Disclosure1 |
"CVE-2026–53923: How a 32-Bit Integer in vLLM Leaks One User’s GPU Memory Into Another’s" by Aviral Srivastava #InfoSec #CyberSecurity #Hacking #BugBounty https://medium.com/@aviral23/cve-2026-53923-how-a-32-bit-integer-in-vllm-leaks-one-users-gpu-memory-into-another-s-7f726bf5bb23
Post summary
The article announces a new vulnerability in vLLM where a 32‑bit integer flaw leads to GPU memory leakage between users.
🚨*CVE* CVE-2026-53923 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 dequantiz… https://www.cve.org/CVERecord?id=CVE-2026-53923 ----- Traducción: CVE-2026-53923 vLL… http://infoflow.cloud`
Post summary
The post announces CVE-2026-53923, a vulnerability in vLLM involving integer truncation during GGUF dequantization, and provides a link to the official CVE record.
CVE-2026-53923 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 dequantiz… https://www.cve.org/CVERecord?id=CVE-2026-53923
Post summary
CVE-2026-53923 exposes an integer truncation vulnerability in vLLM’s GGUF dequantization from versions 0.5.5 to 0.23.1rc0.
1 of 1 entries
| Part | Vendor | Product | Version | Target SW | Target HW |
|---|---|---|---|---|---|
| App | vllm | vllm | - | - | - |