vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

Executive SummaryThe follow-up protection for CVE-2025-62164 is incomplete at vLLM revision 26587f9519e22a5c4549ead7595ad9ca3229c4fd. It wraps serialized prompt-embedding reconstruction and dense conversion in torch.sparse.checksparsetensorinvariants, but PyTorch 2.11.0 implements that context wi...

GHSA-PR7F-P5MW-FC87 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

Executive Summary The follow-up protection for CVE-2025-62164 is incomplete at vLLM revision 26587f9519e22a5c4549ead7595ad9ca3229c4fd. It wraps serialized prompt-embedding reconstruction and dense conversion in torch.sparse.checksparsetensorinvariants, but PyTorch 2.11.0 implements that context...

vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

Executive Summary The follow-up protection for CVE-2025-62164 is incomplete at vLLM revision 26587f9519e22a5c4549ead7595ad9ca3229c4fd. It wraps serialized prompt-embedding reconstruction and dense conversion in torch.sparse.checksparsetensorinvariants, but PyTorch 2.11.0 implements that context...

EUVD-2026-58064

vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts...

CVE-2026-73557

A flaw was found in vLLM, an inference and serving engine for large language models. An incomplete remediation for a previous vulnerability CVE-2025-62164 can be bypassed. This occurs when concurrent prompt parts are processed, leading to a race condition in the handling of sparse tensors. This...

CVE-2026-73557

CVE-2026-73557 affects vLLM between 0.20.2rc0 and 0.26.0. The flaw arises in safe_load_prompt_embeds in vllm/renderers/embed_utils.py, where using torch.sparse.check_sparse_tensor_invariants with a process-global save/enable/restore state can be raced via concurrent prompt_embeds (POST /v1/chat/c...

CVE-2026-73557 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

CVE-2026-73557 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

PT-2026-71672

Name of the Vulnerable Software and Affected Versions vLLM versions 0.20.2rc0 through 0.25.x Description A race condition exists in the safe load prompt embeds function within vllm/renderers/embed utils.py when enable prompt embeds is enabled. The issue occurs because torch.sparse.check sparse...

PT-2026-51172

Name of the Vulnerable Software and Affected Versions vLLM versions 0.10.2 through 0.12.x Description Multimodal embeddings processing lacks sparse tensor validation. Since PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests containing...

vLLM introduced enhanced protection for CVE-2025-62164

Summary The fix here for CVE-2025-62164 is not sufficient. The fix only disables prompt embeds by default rather than addressing the root cause, so the DoS vulnerability remains when the feature is enabled. Details vLLM's pending change attempts to fix the root cause, which is the missing sparse...

CVE-2025-62164

creationtimestamp| type| source ---|---|--- 2025-11-21 03:18:47+00:00| seen| https://bsky.app/profile/cve.skyfleet.blue/post/3m64d4stlz72s 2025-11-21 17:15:20+00:00| seen| https://bsky.app/profile/checkmarxzero.bsky.social/post/3m65rvmma7d2j 2025-11-24 03:39:31+00:00| seen|...