Resource exhaustion in Vllm
CVE-2026-71486
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.
Vulnerability class: DoS (Denial of Service)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 4.3 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L.
EPSS exploit prediction
EPSS 0.004, 31.8th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Vllm
- Vllm-Project Vllm — versions < 0.26.0
Weakness classification (CWE)
Public exploits and proof-of-concept code
1 public repository with exploit or proof-of-concept code for this CVE:
- tmvictorpeters/jbo4rgl (last pushed 2026-10-05): r30xlqo6从一个辅助 API 看资源边界:CVE-2026-71486(vLLM)w680rjb2afux
References
- https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b (Patch)
- https://github.com/vllm-project/vllm/pull/47260 (Patch, Issue Tracking)
- 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, Mitigation, Vendor Advisory)
This CVE has public exploit evidence. See the latest CVEs with public exploits.