CVE-2026-73557

Published: Ago 13, 2026 Last Modified: Ago 13, 2026

ExploitDB:

Other exploit source:

Google Dorks:

MEDIUM 6,3

Source: [email protected]

Attack Vector: network

Attack Complexity: low

Privileges Required: none

User Interaction: none

Confidentiality: N/A

Integrity: N/A

Availability: N/A

Description

AI Translation Available

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.

362

Concurrent Execution using Shared Resource with Improper Synchronization ('Race Condition')

Draft

Abstraction: Class Structure: Simple

Common Consequences

Security Scopes Affected:

Availability Confidentiality Integrity Access Control

Potential Impacts:

Dos: Resource Consumption (Cpu) Dos: Resource Consumption (Memory) Dos: Resource Consumption (Other) Dos: Crash, Exit, Or Restart Dos: Instability Read Files Or Directories Read Application Data Execute Unauthorized Code Or Commands Gain Privileges Or Assume Identity Bypass Protection Mechanism