Veille CVE
CVE-2026-73557
5.3 MoyenneDescription
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.
Produits concernés
Scores CVSS
| Version | Score | Source | Vecteur |
|---|---|---|---|
| 4.0 | 6.3 Moyenne | security-advisories@github.com | 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 |
| 3.1 | 5.3 Moyenne | nvd@nist.gov (NVD) | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L |
Faiblesses (CWE)
Références
- https://github.com/vllm-project/vllm/commit/793cf79c89d4049124e756915468ac30318f2e50 Patch
- https://github.com/vllm-project/vllm/pull/48583 Issue TrackingPatch
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-pr7f-p5mw-fc87 MitigationVendor Advisory