Not a U.S. government website. NDD is an independent vulnerability database by Volerion and is not affiliated with or endorsed by NIST or NVD.
VOLERION
Volerion Security Research

NOT DEFERRED DATABASE

VULNERABILITIES

CVE-2026-73557 Details

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.

Metrics

CVSS 3.x Severity and Vector Strings:

References to Advisories, Solutions, and Tools

By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.

Weakness Enumeration

CWE-IDCWE NameSource
CWE-362Concurrent Execution using Shared Resource with Improper Synchronization ('Race Condition')[email protected]

Affected Products

ProductVersions
vllm vllm
>= 0.21.0, < 0.26.0

CPE

  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

Remediation

  • No remediation found in references.

Change History

3 change records found show changes


QUICK INFO

CVE Dictionary Entry:
CVE-2026-73557
NVD Published Date:
Aug 13, 2026
NVD Last Modified:
Oct 15, 2026
Source:
[email protected]