VulnerabilityAwaiting Analysis

CVE-2026-73557

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…

MEDIUM 6.3EPSS 0.25%

Does this matter?

Lower severity and a low EPSS score (0.25%). Track it; it rarely justifies an emergency change on its own.

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.

CVSS 4.0: 6.3 MEDIUMCVSS: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/M
EPSS: 0.25% probability · 17th percentile
CISA KEV: Not listed
Weakness: CWE-362
Source: security-advisories@github.com

References

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.