CVE-2026-73557 Details
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.
Metrics
CVSS 4.0 Severity and Vector Strings:
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
CISA-ADP
Assessed Aug 13, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://github.com/vllm-project/vllm/commit/793cf79c89d4049124e756915468ac30318f2e50 | [email protected] | Patch |
| https://github.com/vllm-project/vllm/pull/48583 | [email protected] | Issue TrackingPatch |
| https://github.com/vllm-project/vllm/releases/tag/v0.26.0 | [email protected] | Release Notes |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-pr7f-p5mw-fc87 | [email protected] | MitigationVendor Advisory |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-362 | Concurrent Execution using Shared Resource with Improper Synchronization ('Race Condition') | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| vllm vllm | >= 0.21.0, < 0.26.0 |
CPE
Remediation
| |
Change History
3 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Oct 15, 2026 | Initial Analysis | [email protected] |
| Aug 13, 2026 | CVE Modified | CISA-ADP |
| Aug 13, 2026 | New CVE Received | [email protected] |