Vulnerability · Published Aug 13, 2026 · Assigned by GitHub_M
CVE-2026-73557vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts
Medium 6.3
In plain English
A medium-severity race condition in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.2% (higher than 16% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | vllm | 0.26.0 | GHSA-pr7f-p5mw-fc87 |
| PyPI | vllm | 0.26.0 | PYSEC-2026-3938 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.20.2rc0, < 0.26.0 |
Weakness: CWE-362 · Vector: CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-pr7f-p5mw-fc87 x_refsource_CONFIRM
- https://github.com/vllm-project/vllm/pull/48583 x_refsource_MISC
- https://github.com/vllm-project/vllm/commit/793cf79c89d4049124e756915468ac30318f2e50 x_refsource_MISC
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0 x_refsource_MISC