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:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:LWeakness enumeration
Affected software
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.20.2rc0, < 0.26.0 |
References
- https://github.com/vllm-project/vllm/commit/793cf79c89d4049124e756915468ac30318f2e50Patch
- https://github.com/vllm-project/vllm/pull/48583Issue Tracking, Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-pr7f-p5mw-fc87Mitigation, Vendor Advisory
Timeline
- Published
- Aug 13, 2026
- Last modified
- Oct 15, 2026
- NVD status
- Analyzed