{"id":"CVE-2026-73557","aliases":["GHSA-pr7f-p5mw-fc87"],"url":"https://o3.security/vulnerability/CVE-2026-73557","summary":"vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts","details":"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.","published":"2026-08-13T15:00:15.746Z","modified":"2026-08-15T11:47:58.345174652Z","cvss":null,"epss":null,"cisaKev":null,"exploitsKnown":null,"affectedPackages":[{"ecosystem":"PyPI","name":"vllm","fixedVersion":"0.26.0"}],"fix":{"url":"https://github.com/vllm-project/vllm/commit/793cf79c89d4049124e756915468ac30318f2e50","label":"vllm-project/vllm@793cf79"},"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/releases/tag/v0.26.0"},{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/73xxx/CVE-2026-73557.json"},{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-pr7f-p5mw-fc87"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-73557"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/commit/793cf79c89d4049124e756915468ac30318f2e50"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/pull/48583"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-08-15T11:47:58.345174652Z"}}