CVE-2026-115916 — Vllm Vllm (tüm Sürümler) — CWE-129 · CWE-193
CVE-2026-115916 is a MEDIUM severity security vulnerability (CWE-129, CWE-193) (CVSS 6.5/10) affecting Vllm Vllm (tüm Sürümler). Technical vector analysis shows that an attacker can exploit this flaw remotely over the network with low-privileged access (PR:L) with zero user interaction (UI:N), causing high-impact service disruption (A:H).
📄 Official NVD / MITRE Original Record Text
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.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CVE-2026-115916
CVSS 6.5/10 · MEDIUM · 26.10.2026
CWE: CWE-129, CWE-193
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🎯 WHAT IS THIS VULNERABILITY?
Summary: 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…
Affected: vllm:vllm
⚡ ATTACK CHAIN
Remotely over internet | low-privilege account | no user interaction | low complexity.
🌍 REAL WORLD IMPACT
Service can be completely taken down.
🛡️ REMEDIATION
→ Apply vendor security update for vllm:vllm.
→ Add WAF rule, create IDS alert for anomalous traffic.
⚠️ URGENCY
📋 Routine update cycle (30 days)
────────────────────────────────────────
[Kural Tabanlı Otomatik Güvenlik Analizi]
FOFA Query