CVE-2026-73557

Source
https://cve.org/CVERecord?id=CVE-2026-73557
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-73557.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2026-73557
Aliases
  • GHSA-pr7f-p5mw-fc87
Published
2026-08-13T15:00:15.746Z
Modified
2026-08-15T11:47:58.345174652Z
Severity
  • 6.3 (Medium) CVSS_V4 - CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N CVSS Calculator
Summary
vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts
Details

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.

Database specific
{
    "cna_assigner": "GitHub_M",
    "cwe_ids": [
        "CWE-362"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/73xxx/CVE-2026-73557.json"
}
References

Affected packages

Git / github.com/vllm-project/vllm

Affected ranges

Type
GIT
Repo
https://github.com/vllm-project/vllm
Events
Database specific
Show details
{
    "extracted_events": [
        {
            "introduced": "0.20.2rc0"
        },
        {
            "fixed": "0.26.0"
        }
    ],
    "source": [
        "AFFECTED_FIELD",
        "REFERENCES"
    ]
}

Affected versions

v0.*
v0.20.2rc0
v0.21.1rc0
v0.22.1rc0
v0.23.1rc0
v0.25.0
v0.26.0rc1

Database specific

source
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-73557.json"