CVE-2026-73557

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.

CVSS

No CVSS.

References

Link	Resource
https://github.com/vllm-project/vllm/commit/793cf79c89d4049124e756915468ac30318f2e50
https://github.com/vllm-project/vllm/pull/48583
https://github.com/vllm-project/vllm/releases/tag/v0.26.0
https://github.com/vllm-project/vllm/security/advisories/GHSA-pr7f-p5mw-fc87

Configurations

No configuration.

History

No history.

Information

Published : 2026-08-13 15:20

Updated : 2026-09-09 20:58

NVD link : CVE-2026-73557

Mitre link : CVE-2026-73557

CVE.ORG link : CVE-2026-73557

JSON object : View

Products Affected

No product.

CWE

CWE-362

Concurrent Execution using Shared Resource with Improper Synchronization ('Race Condition')

{"id": "CVE-2026-73557", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-73557", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-08-13T17:50:06.312927Z"}}], "cvssMetricV40": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 6.3, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "valueDensity": "NOT_DEFINED", "vectorString": "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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "NONE", "attackComplexity": "LOW", "attackRequirements": "PRESENT", "privilegesRequired": "NONE", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "NONE", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "LOW", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "NONE", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"status": "affected", "version": ">= 0.20.2rc0, < 0.26.0"}]}]}], "published": "2026-08-13T15:20:18.080", "references": [{"url": "https://github.com/vllm-project/vllm/commit/793cf79c89d4049124e756915468ac30318f2e50", "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/pull/48583", "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0", "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-pr7f-p5mw-fc87", "source": "security-advisories@github.com"}], "vulnStatus": "Awaiting Analysis", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-362"}]}], "descriptions": [{"lang": "en", "value": "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."}], "lastModified": "2026-09-09T20:58:37.713", "sourceIdentifier": "security-advisories@github.com"}