CVE-2026-90878: A vulnerability was determined in vllm-project vLLM up to 0.27.1. This affects an unknown part of the file /v1/chat/comp
Summary
A vulnerability was found in vLLM (a library for running large language models) version 0.27.1 and earlier, where attackers can manipulate the chat_template parameter to cause excessive resource consumption through Jinja template rendering (a system for dynamically generating text). The vulnerability can be exploited remotely, and a fix has been proposed but not yet officially accepted.
Vulnerability Details
4.3(medium)
EPSS: 0.0%
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
network
low
low
none
September 15, 2026
Classification
Affected Vendors
Related Issues
CVE-2026-47482: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause missing release of memory
CVE-2022-29200: TensorFlow is an open source platform for machine learning. Prior to versions 2.9.0, 2.8.1, 2.7.2, and 2.6.4, the implem
Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-90878
First tracked: September 15, 2026 at 02:08 AM
Classified by LLM (prompt v3) · confidence: 92%