CVE-2026-93841 vLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token IDs

What is CVE-2026-93841?

CVE-2026-93841 is a medium-severity memory corruption vulnerability in Vllm Vllm, published on 18 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

Official description

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

Weakness: CWE-129

Which versions are affected by CVE-2026-93841?

1 open source package ship an affected version, including vllm. It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2026-93841?

Upgrade vllm to 0.30.0 or later.

Upgrade to the fixed version. Memory-safe languages, compiler hardening and fuzzing prevent most new cases. More about Memory corruption.

Is CVE-2026-93841 being exploited?

There is no known exploitation of CVE-2026-93841 in the wild and no public exploit code.

Other vulnerabilities in Vllm Vllm

• CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration Critical 10.0
• CVE-2026-22778 vLLM leaks a heap address when PIL throws an error Critical 9.8
• CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service Critical 9.8
• CVE-2024-11041 Remote Code Execution in vllm-project/vllm Critical 9.8
• CVE-2026-48746 vLLM: OpenAI auth bypass Critical 9.1

All Vllm Vllm vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• How this page is made

Also known as GHSA-q9hm-g73w-q6wp, MINI-p796-rv9r-rgqj, MINI-r47v-q555-v6cw, MINI-rjr5-qrmp-jqgv, PYSEC-2026-3999.