CVE-2026-73558Medium· 5.3▾ SunlitvLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a reque…
▾ Sunlit zone — Low / medium · no exploitation signal
impact 29.2 · likelihood 0.1 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Exploit-prediction probability, daily snapshots since Sep 8.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
0.3%
Last analysed / modified upstream
0.3% → 0.3%
vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0.
Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Affected packages:
vllm < 0.27.0Patched in:
vllm 0.27.0Connected by shared product, vendor, weakness, or advisory.
CVE-2026-73560Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-71486Medium· 4.3vLLM is an inference and serving engine for large language models
CVE-2026-73555Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-73556Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-73557MediumvLLM is an inference and serving engine for large language models
CVE-2025-47277Critical· 9.8vLLM Allows Remote Code Execution via PyNcclPipe Communication Service