threatdeck
Live 14:45 UTC ·

AI Stack Alert Medium CVE-2026-115916 For AI Eng, SOC / IR, AppSec, CISO AI-assisted

vLLM < 0.32.0: out-of-vocabulary prompt token id crashes engine (CVE-2026-115916)

vLLM versions before 0.32.0 accept a pre-tokenized prompt token id equal to the vocabulary size for models whose vocab is a multiple of 64, such as Llama-2 (vocab 32000). At tensor-parallel size 1 the id reaches an embedding lookup out of range, raising a CUDA device-side assert that takes the engine down. The fix is in 0.32.0.

Why it matters

Any client that can send pre-tokenized input can crash the inference engine with one request, a denial of service. Deployments running tp=1 with affected models are exposed.

Do this

  1. Upgrade vLLM to 0.32.0 or later.
  2. Until patched, reject or filter token-id prompts (for example /v1/completions with prompt as token ids) that contain ids >= the model vocabulary size.
  3. Identify deployments running tensor-parallel size 1 with Llama-2-family or other vocab-size-multiple-of-64 models and prioritize them for upgrade.
  4. Monitor engine logs for CUDA device-side assert errors and engine restarts as indicators of this issue.

Exploit Clock

Exploitation unlikely (for now)

  • EPSS 0.31%

Signals

  • NoCISA KEV
  • 6.5CVSS
  • 0.31%EPSS
  • 27/100Priority
  • 85%Confidence

Evidence

“a single request carrying a pre-tokenized prompt with token id equal to the vocab size (32000) passes vLLM's input-id validation”

GitHub Security Advisories (AI packages)

“which poisons the engine's CUDA context and takes the engine down”

GitHub Security Advisories (AI packages)

“Fixed in [MR59491](https://github.com/vllm-project/vllm/pull/59491), released in v0.32.0.”

GitHub Security Advisories (AI packages)

Sources

Affected / related

vLLM, Llama-2 family, out-of-vocabulary token id input validation bypass

Published 2026-10-28 21:15 UTC · updated 2026-11-08 02:42 UTC · AI-assisted summary, checked against quoted sources · How we score

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.