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 products
vllm: vllm
References4
- github.com/vllm-project/vllm/security/advisories/GHSA-pr7f-p5mw… MitigationVendor Advisory
- github.com/vllm-project/vllm/commit/793cf79c89d4049124e75691546… Patch
- github.com/vllm-project/vllm/pull/48583 Issue TrackingPatch
- github.com/vllm-project/vllm/releases/tag/v0.26.0 Release Notes
Metrics
- CVSS 3.1
-
5.3
MEDIUM
Score source: NVD
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L - CVSS 4.0
-
6.3
MEDIUM
Score source: CNA
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 - EPSS — exploit probability
- 0% percentile: 16 · as of 12 November 2026
- CWE
- CWE-362
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.