7.1
HIGH CVSS 4.0
CVE-2026-100654
vLLM before 0.29.0 Denial of Service via out-of-range stop_token_ids
Description

vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates only that the values are integers, not that each token id is within the model vocabulary/logits range. When min_tokens > 0, the stop token ids are used as logits indices to suppress stop tokens, so an out-of-range id reaches a CUDA indexing operation (index_put_) and triggers a device-side assertion. An authenticated API user can send a single malformed completion request that returns 500 Internal Server Error and puts EngineCore into a fatal state, causing subsequent requests to fail until the service is restarted (denial of service).

INFO

Published Date :

Sept. 26, 2026, 2:16 p.m.

Last Modified :

Sept. 26, 2026, 2:16 p.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2026-100654 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

ID Vendor Product Action
1 Vllm-project vllm
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 3.1 MEDIUM 83251b91-4cc7-4094-a5c7-464a1b83ea10
CVSS 3.1 MEDIUM MITRE-CVE
CVSS 3.1 MEDIUM [email protected]
CVSS 4.0 HIGH 83251b91-4cc7-4094-a5c7-464a1b83ea10
CVSS 4.0 HIGH [email protected]
Solution
Update vLLM to version 0.29.0 or later to fix the denial of service vulnerability.
  • Update vLLM to version 0.29.0 or later.
  • Apply the vendor-supplied patch.
  • Validate that stop_token_ids are within model vocabulary.
  • Restart the service if it is in a fatal state.
References to Advisories, Solutions, and Tools

Here, you will find a curated list of external links that provide in-depth information, practical solutions, and valuable tools related to CVE-2026-100654.

URL Resource
https://github.com/vllm-project/vllm/security/advisories/GHSA-v5gm-qgmv-gc6c
https://www.vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-out-of-range-stop-token-ids
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-100654 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-100654 weaknesses.

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-100654 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-100654 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • New CVE Received by [email protected]

    Sep. 26, 2026

    Action Type Old Value New Value
    Added Description vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates only that the values are integers, not that each token id is within the model vocabulary/logits range. When min_tokens > 0, the stop token ids are used as logits indices to suppress stop tokens, so an out-of-range id reaches a CUDA indexing operation (index_put_) and triggers a device-side assertion. An authenticated API user can send a single malformed completion request that returns 500 Internal Server Error and puts EngineCore into a fatal state, causing subsequent requests to fail until the service is restarted (denial of service).
    Added CVSS V4.0 AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
    Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
    Added CWE CWE-129
    Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/100xxx/CVE-2026-100654.json">CVE-2026-100654</a>
    Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-v5gm-qgmv-gc6c
    Added Reference https://www.vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-out-of-range-stop-token-ids
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.