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.

• CWE-362

• 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

Published

Aug 13, 2026

Last Modified

Oct 15, 2026

Status

Analyzed

• How Strix found a critical auth bypass in etcdStrix autonomously discovered a critical authentication bypass in etcd, later designated CVE-2026-33413.
• Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
• PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
• AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.

• CVE-2026-73550Envoy is an open source edge and service proxy designed for …7.5
• CVE-2026-73551Envoy is an open source edge and service proxy designed for …5.3
• CVE-2026-73552Envoy is an open source edge and service proxy designed for …7.5
• CVE-2026-73553Envoy is an open source edge and service proxy designed for …7.5
• CVE-2026-73555vLLM is an inference and serving engine for large language m…5.3
• CVE-2026-73556vLLM is an inference and serving engine for large language m…5.3
• CVE-2026-73558vLLM is an inference and serving engine for large language m…5.3
• CVE-2026-73559vLLM is an inference and serving engine for large language m…6.5
• CVE-2026-7356Use after free in Navigation in Google Chrome prior to 147.0…8.8
• CVE-2026-73560vLLM is an inference and serving engine for large language m…6.5
• CVE-2026-73561Hub is a Node.js WebSocket server and client with added feat…7.5
• CVE-2026-73562Mongoose is a MongoDB object modeling tool designed to work …6.5