Out-of-bounds Write Affecting vllm package, versions [0,]
Threat Intelligence
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-PYTHON-VLLM-20044413
- published22 Sept 2026
- disclosed18 Sept 2026
- creditUnknown
Introduced: 18 Sep 2026
NewCVE-2026-93841 (opens in a new tab)How to fix?
A fix was pushed into the master branch but not yet published.
Overview
vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs
Affected versions of this package are vulnerable to Out-of-bounds Write via the Triton _bincount_kernel, where prompt token IDs index the penalty prompt-presence bitset without bounds checking against the vocabulary size. An attacker can submit multimodal audio requests containing tokens equal to the vocabulary size, triggering out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.