CVE-2026-73557: vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

Published Aug 13, 2026
·
Updated

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts submitted to POST /v1/chat/completions through AsyncMultiModalItemTracker.resolveitems, asyncio.gather, and the default executor, allowing an invalid sparse tensor to reach tensor.todense despite the CVE-2025-62164 guard when enablepromptembeds is enabled. This issue is fixed in version 0.26.0.

Affected Software

1 affected component
vllm>=0.20.2rc0<0.26.0

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade to a fixed release to a version that resolves this vulnerability.

    Fixed in 0.26.0

Event History

Aug 13, 2026
CVE Published
via MITRE·03:00 PM
Data Sourced
via MITRE·03:00 PM
DescriptionWeakness
Free Weekly Intel

Don't miss critical vulnerabilities

Join thousands of security professionals who receive our weekly digest of trending CVEs, zero-days, and exploited vulnerabilities.

No spam. Unsubscribe anytime.

Frequently Asked Questions

1

What is the severity of CVE-2026-73557?

The severity of CVE-2026-73557 is rated at 65.

2

How do I fix CVE-2026-73557?

To fix CVE-2026-73557, update vLLM to version 0.26.0 or later.

3

What type of vulnerability is CVE-2026-73557?

CVE-2026-73557 is classified as a Race Condition vulnerability.

4

What versions of vLLM are affected by CVE-2026-73557?

CVE-2026-73557 affects vLLM versions from 0.20.2rc0 until 0.26.0.

5

What components are involved in CVE-2026-73557?

CVE-2026-73557 specifically involves the safe_load_prompt_embeds function in vllm/renderers/embed_utils.py.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203