Skip to content
fr Sign in
6.5 Medium

CVE-2026-115916 vLLM is an inference and serving engine for large language models

Description

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0.

Affected products and versions

Product Affected versions Fixed in
vllm 0.32 earliest → < 0.32.0 0.32.0

References

Timeline

  1. Published
  2. Last modified

Other CVEs of vllm

The 121 CVEs of vllm →
CVE-2026-115918 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115917 vLLM is an inference and serving engine for large language models 3.4 Low CVE-2026-115915 vLLM is an inference and serving engine for large language models 8.1 High CVE-2026-115914 vLLM is an inference and serving engine for large language models 6.5 Medium
Track this CVE