Analysis and contextual insights are available on OpenCVE Cloud.
No vendor fix or workaround currently provided.
Additional remediation guidance may be available on OpenCVE Cloud.
Tracking
Sign in to view the affected projects.
No advisories yet.
Thu, 13 Aug 2026 15:15:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts | |
| Weaknesses | CWE-362 | |
| References |
| |
| Metrics |
cvssV4_0
|
Subscriptions
No data.
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-08-13T15:00:15.746Z
Reserved: 2026-08-12T20:53:46.380Z
Link: CVE-2026-73557
No data.
Status : Received
Published: 2026-08-13T15:20:18.080
Modified: 2026-08-13T15:20:18.080
Link: CVE-2026-73557
No data.
OpenCVE Enrichment
No data.