Strix
64.8K

CVE-2026-71486

MEDIUMCVSS 4.3/10EPSS 0.34%

Last modified

CVE-2026-71486 is a medium-severity vulnerability rated 4.3/10 on the CVSS scale. 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. EPSS estimates a 0.34% chance of exploitation in the next 30 days.

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.

Metrics

CVSS 3.1
4.3/10

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L

EPSS Probability
0.34%

27.2th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

Source: CNA advisory (CVE.org). NVD analysis pending.

VendorProductVersions
vllm-projectvllm< 0.26.0

References

Timeline

Published
Last Modified
Status
Awaiting Analysis

Frequently Asked Questions

What is 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.
How severe is CVE-2026-71486?
CVE-2026-71486 has a CVSS score of 4.3/10 (MEDIUM severity). The EPSS model estimates a 0.34% probability of exploitation in the next 30 days.
How do I fix CVE-2026-71486?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2026

View all 2026CVEs →

Are you affected by CVE-2026-71486?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST