cve.bz

CVE-2026-115916 vllm vllm: Improper Validation of Array Index

6.5 mediumEPSS 0.3%Fix available

Medium (6.5) in vllm vllm. EPSS 0.3% estimated probability of exploitation activity in the next 30 days. Fixed in vllm 0.32.0.

On this page
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.

Severity

CVSS 3.1

6.5 medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS
0.3% (unchanged from 0.3% a week ago) estimated probability of exploitation activity in the next 30 days; 24th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CWEs
CWE-129 Improper Validation of Array Index
CWE-193 Off-by-one Error
OWASP Top 10
A05:2025 Injection
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-115916 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-115916?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-115916?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-115916 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the NVD's CPE matches.

ProductAffected
vllm:vllmbefore 0.32.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-q97c-p368-75c4PyPIvllm<0.32.00.32.0
PYSEC-2026-4347PyPIvllm<0.32.00.32.0

Red Hat

Red Hat rates this Moderate.

Red Hat's statement

Red Hat has rated this issue as Moderate severity because it results exclusively in a denial of service by terminating the model serving process without allowing unauthorized data access, privilege escalation, or system compromise. In environments such as Red Hat OpenShift AI and Red Hat AI Inference Server, exploitation is limited to configurations utilizing single-GPU instances (tensor parallelism of one) hosting specific models with vocabularies aligned to multiples of 64. Furthermore, multi-GPU deployments with higher tensor parallelism mask token inputs, which naturally prevents the crash condition.

ProductPackageStateAdvisory
Red Hat AI Inference Serverrhaii-fast/vllm-cpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-cuda-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-gaudi-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-neuron-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-omni-cuda-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-rocm-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-spyre-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-tpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-cpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-cuda-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-gaudi-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-neuron-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-rocm-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-spyre-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-tpu-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-aws-cuda-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-azure-cuda-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-azure-rocm-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-cuda-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-gaudi-rhel9Fix deferred
11 more in the JSON and on Red Hat's page.

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-115916.

Attack patterns (CAPEC)

  • CAPEC-100 Overflow Buffers Likelihood: High · Severity: Very High

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON