CVEvulnerability

CVE-2026-73557

6.3 MEDIUM Published 2026-08-13 Modified 2026-10-15 Official page ↗
Status
Analyzed
Published
2026-08-13
Last modified
2026-10-15
Assigner
[email protected]
CVSS 4.0 ([email protected])
6.3 MEDIUM — 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
CVSS 3.1 ([email protected])
5.3 MEDIUM — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
Weaknesses
CWE-362

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.

Affected configurations

• vllm vllm (>= 0.21.0 < 0.26.0)

Related

Weakness · CWE (1)

  • CWE-362 Concurrent Execution using Shared Resource with Improper Synchronization weakness

References