CVE-2026-71486
Description
A flaw was found in vLLM. An authenticated API client can exploit derender endpoints by providing oversized GenerateResponse objects. These endpoints process the objects without enforcing output bounds or response-size limits. This can lead to excessive consumption of CPU and memory resources, resulting in a Denial of Service (DoS).
Statement
A moderate severity denial of service flaw was found in vLLM, the LLM inference and serving engine shipped in Red Hat AI Inference Server and Red Hat Enterprise Linux AI. The /v1/completions/derender and /v1/chat/completions/derender API endpoints accept caller-supplied GenerateResponse objects and process their generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts structures through OnlineDerenderer and tokenizer.decode before limits such as max_model_len, max_tokens, max_num_seqs, or response-size restrictions are enforced. As a result, an authenticated API client can submit oversized GenerateResponse objects and cause excessive CPU and memory consumption, potentially producing oversized responses and degrading or denying service for other users of the vLLM instance. The affected Red Hat AI Inference Server and Red Hat Enterprise Linux AI streams are currently marked for a deferred fix; until a remediated update is delivered, deployments that expose the vLLM API to lower-trust authenticated clients retain residual risk of resource-exhaustion attacks. Red Hat and upstream both rate this issue Moderate (CVSS 4.3, CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L), reflecting the availability-only impact and the credentials required to exploit it.
Mitigation
Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability. The upstream vLLM project has fixed this issue; updating to a release that includes the upstream fix is recommended once it becomes available for the affected Red Hat products.
Common Vulnerability Scoring System (CVSS) Score Details
Info alert:Important note
CVSS scores for open source components depend on vendor-specific factors (e.g. version or build chain). Therefore, Red Hat's score and impact rating can be different from NVD and other vendors. Red Hat remains the authoritative CVE Naming Authority (CNA) source for its products and services (see Red Hat classifications).
CVSS v3 Score Breakdown
| Red Hat | NVD | cve.org | |
|---|---|---|---|
| Base Score | 4.3 | N/A | 4.3 |
| Attack Vector | Network | N/A | Network |
| Attack Complexity | Low | N/A | Low |
| Privileges Required | Low | N/A | Low |
| User Interaction | None | N/A | None |
| Scope | Unchanged | N/A | Unchanged |
| Confidentiality | None | N/A | None |
| Integrity Impact | None | N/A | None |
| Availability Impact | Low | N/A | Low |
Vector
Red Hat: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
cve.org: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.
