CVEvulnerability
CVE-2026-71486
4.3 MEDIUM
Official page ↗
- Status
- Analyzed
- Published
- 2026-08-17
- Last modified
- 2026-10-23
- Assigner
- [email protected]
- CVSS 3.1 ([email protected])
- 4.3 MEDIUM — CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
- Weaknesses
- CWE-400, CWE-770
Description
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 configurations
• vllm vllm (< 0.26.0)
Related
References
- https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b Patch
- https://github.com/vllm-project/vllm/pull/47260 Issue Tracking, Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff Exploit, Vendor Advisory, Mitigation