CVE-2026-73557
vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts
CVSS Score
0.0
EPSS Score
0.0%
EPSS Percentile
0th
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 | CWE-362 |
| Vendor | vllm-project |
| Product | vllm |
| Published | Aug 13, 2026 |
Stay Ahead of the Next One
Get instant alerts for vllm-project vllm
Be the first to know when new unknown vulnerabilities affecting vllm-project vllm are published — delivered to Slack, Telegram or Discord.
Get Free Alerts →
Free · No credit card · 60 sec setup
Affected Versions
vllm-project / vllm
>= 0.20.2rc0, < 0.26.0
References
github.com: https://github.com/vllm-project/vllm/security/advisories/GHSA-pr7f-p5mw-fc87 github.com: https://github.com/vllm-project/vllm/pull/48583 github.com: https://github.com/vllm-project/vllm/commit/793cf79c89d4049124e756915468ac30318f2e50 github.com: https://github.com/vllm-project/vllm/releases/tag/v0.26.0