vllm-project · vLLM · published 2026-08-13

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

Routine No exploitation evidence; EPSS 0.2%.

CVE-2026-73557 is not known to be exploited in the wild. EPSS estimates a 0.2% chance of exploitation in the next 30 days, higher than 16% of all CVEs. This vLLM vulnerability: CVSS 6.3 (v4.0). Fixed upstream in vLLM 0.26.0. Routine: patch when convenient.

Share this

Remediation#

Fixed upstream in vLLM 0.26.0.

Patch events

  1. This monthSecurity release

    AI toolingvLLM

    vLLM security release: 0.26.0

    Upgrade to 0.26.0

    Why: CVE-2026-73559: Public proof-of-concept exists (SSVC exploitation: poc).

Exploit intelligence#

SignalValueSource
Known exploitedNoCISA KEV
Ransomware use—CISA KEV
EPSS (30-day exploitation probability)0.2% (16th pct)FIRST EPSS v2026.06.15
CVSS base score6.3 (v4.0)
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
CNA / CISA ADP
SSVC exploitationnoneCISA Vulnrichment
SSVC automatableNoCISA Vulnrichment
SSVC technical impactpartialCISA Vulnrichment

Affected versions (from the CVE record)#

Description (from the CVE record)#

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

Quoted from the CVE Program record.

Elsewhere#

Distro status: Debian · Ubuntu · Red Hat · Alpine

Something wrong on this page?
Anonymous. Reports are checked against the primary source.

Also on today's list

See today's list → · Coming up →