CVE-2026-71486
Published:August 17, 2026
Updated:August 31, 2026
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts structures are processed by OnlineDerenderer and tokenizer.decode before max_model_len, max_tokens, max_num_seqs, or response-size limits are enforced, allowing an authenticated API client to consume excessive CPU and memory and produce oversized responses. This issue is fixed in version 0.26.0.
Affected Packages
vllm (CONDA):
Affected version(s) >=0.8.3 <0.26.0Fix Suggestion:
Update to version 0.26.0https://github.com/vllm-project/vllm.git (GITHUB):
Affected version(s) >=v0.1.0 <v0.26.0Fix Suggestion:
Update to version v0.26.0vllm (PYTHON):
Affected version(s) >=0.0.1 <0.26.0Fix Suggestion:
Update to version 0.26.0Related Resources (6)
Do you need more information?
Contact UsCVSS v4
Base Score:
5.3
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
LOW
User Interaction
NONE
Vulnerable System Confidentiality
NONE
Vulnerable System Integrity
NONE
Vulnerable System Availability
LOW
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
4.3
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
LOW
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
NONE
Availability
LOW
Weakness Type (CWE)
EPSS
Base Score:
0.34