CVE-2026-73557 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

What is CVE-2026-73557?

CVE-2026-73557 is a medium-severity vulnerability in Vllm Vllm, published on 13 Aug 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

Official description

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.

Weakness: CWE-362

Which versions are affected by CVE-2026-73557?

3 open source packages ship an affected version, including vllm. It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2026-73557?

Upgrade vllm to 0.26.0 or later.

Is CVE-2026-73557 being exploited?

There is no known exploitation of CVE-2026-73557 in the wild and no public exploit code.

Other vulnerabilities in Vllm Vllm

• CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration Critical 10.0
• CVE-2026-22778 vLLM leaks a heap address when PIL throws an error Critical 9.8
• CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service Critical 9.8
• CVE-2024-11041 Remote Code Execution in vllm-project/vllm Critical 9.8
• CVE-2026-48746 vLLM: OpenAI auth bypass Critical 9.1

All Vllm Vllm vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• How this page is made

Also known as GHSA-pr7f-p5mw-fc87, MINI-j7xv-8w99-3p27, MINI-pch5-9p23-8vcq, PYSEC-2026-3938.