Upstream information

CVE-2026-73557 at MITRE

Description

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.

SUSE information

Overall state of this security issue: Does not affect SUSE products

This issue is currently rated as having moderate severity.

CVSS v4 Scores
CVSS detail CNA (GitHub)
Base Score 6.3
Vector 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Attack Vector Network
Attack Complexity Low
Attack Requirements Present
Privileges Required None
User Interaction None
Vulnerable System Confidentiality Impact None
Vulnerable System Integrity Impact None
Vulnerable System Availability Impact Low
Subsequent System Confidentiality Impact None
Subsequent System Integrity Impact None
Subsequent System Availability Impact None
CVSSv4 Version 4.0
SUSE Bugzilla entry: 1275172 [RESOLVED / FIXED]

No SUSE Security Announcements cross referenced.


SUSE Timeline for this CVE

CVE page created: Fri Aug 14 17:40:23 2026
CVE page last modified: Mon Aug 17 12:43:00 2026