AI Threat Alert
CVE-2026-73557
AWAITING NVDvLLM 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...
Full CISO analysis pending enrichment.
How severe is it?
What should I do?
No patch available
Monitor for updates. Consider compensating controls or temporary mitigations.
Which compliance frameworks are affected?
Compliance analysis pending. Sign in for full compliance mapping when available.
Frequently Asked Questions
What is CVE-2026-73557?
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.
Is CVE-2026-73557 actively exploited?
No confirmed active exploitation of CVE-2026-73557 has been reported, but organizations should still patch proactively.
How to fix CVE-2026-73557?
No patch is currently available. Monitor vendor advisories for updates.
What is the CVSS score for CVE-2026-73557?
No CVSS score has been assigned yet.
What are the technical details?
Original Advisory
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.
Weaknesses (CWE)
CWE-362 — Concurrent Execution using Shared Resource with Improper Synchronization ('Race Condition'): The product contains a concurrent code sequence that requires temporary, exclusive access to a shared resource, but a timing window exists in which the shared resource can be modified by another code sequence operating concurrently.
- [Architecture and Design] In languages that support it, use synchronization primitives. Only wrap these around critical code to minimize the impact on performance.
- [Architecture and Design] Use thread-safe capabilities such as the data access abstraction in Spring.
Source: MITRE CWE corpus.