CVE-2026-93841
vLLM through 0.29.0 contains a memory corruption vulnerability in …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L241-L255
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L33-L37
- github.com/vllm-project/vllm/pull/49081
- www.vulncheck.com/advisories/vllm-through-0.29.0-adjacent-request-sampler-state-corruption
- nvd.nist.gov/vuln/detail/CVE-2026-93841
- cve.org/CVERecord?id=CVE-2026-93841
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.