Servers and applications
CVE-2026-53923
GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving
- Severity
- Medium 5.3
- Published
- 11 Jun 2026
- Last changed
- 25 Oct 2026
- Added to UpHeron
- 3 Nov 2026
- Fixed in
- 0.23.1, 0.24.0
- Exploit chance
- 0.5% in the next 30 daysHigher than 42% of CVEs. EPSS by FIRST, 19 Nov 2026
- Attack
- Over the network · No login needed · Needs someone to view a page or file
- Attacker can
- Read some data · Change some data
- CVSS vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X- Also known as
- GHSA-5jv2-g5wq-cmr4
- Sources
- NVD, Project advisories (GitHub)
Description
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.
The to_cuda_ggml_t function pointer type at ggml-common.h:1067 declares its element count parameter as int (32-bit):
All dequantize kernel functions (dequantize_block_cuda, dequantize_row_q2_K_cuda, etc. in dequantize.cuh) inherit this int k parameter and use it as the kernel launch grid size:
In ggml_dequantize() at gguf_kernel.cu:85, the caller passes m * n (an int64_t product) to this int k parameter:
Affected software
| Software | Affected versions |
|---|---|
vLLMServers and applications · cpe:a:vllm:vllm |
|
vLLMServers and applications · github:vllm-project/vllm |
|
About vLLM
open-source software for large language model inference
- Docker Hub pulls
- 44,195,225Docker Hub, 15 Nov 2026
- GitHub stars
- 96,943GitHub, 15 Nov 2026
- Forks
- 24,836GitHub, 15 Nov 2026
- Latest release
- v0.33.0rc3GitHub, 15 Nov 2026
- Released
- 2 Nov 2026GitHub
- License
- Apache Software License 2.0Wikidata
- First published on GitHub
- 9 Feb 2023GitHub
Website Source code Docker image
Vulnerabilities in vLLM
- In our list
- 169
- Published in the last 12 months
- 150
- Critical, last 12 months
- 6
- High, last 12 months
- 63
- Known exploited
- 0
- CVE-2026-130686vLLM 0.6.0 before 0.33.0 Resource Exhaustion via Multi-Image RequestsHigh 8.7 18 Nov 2026
- CVE-2026-130684vLLM before 0.33.0 Path Traversal via speculators_config verifier.name_or_pathMedium 5.3 18 Nov 2026
- CVE-2026-130685vLLM 0.28.0 before 0.33.0 Unauthenticated DoS via Out-of-Range Prompt Token IDHigh 8.7 18 Nov 2026
- GHSA-xgh8-qwjh-q853/v1/systemone bypasses the --trust-request-chat-template gateMedium 6.5 18 Nov 2026
- CVE-2026-129356vllm-project vllm Common Prefix single_type_kv_cache_manager.py race conditionLow 2.3 15 Nov 2026
- CVE-2026-126394vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_framesMedium 6.9 13 Nov 2026
References
- NVD https://nvd.nist.gov/vuln/detail/CVE-2026-53923
- CVE.org https://www.cve.org/CVERecord?id=CVE-2026-53923
- GitHub Advisory Database https://github.com/advisories/GHSA-5jv2-g5wq-cmr4
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4