Lucene search
+L

6 matches found

Snyk
Snyk
•added 2026/08/13 7:00 p.m.•11 views

Race Condition

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Race Condition through the safeloadpromptembeds function in vllm/renderers/embedutils.py when concurrent prompt parts are submitted to the...

6.3CVSS5.5AI score0.00404EPSS
SaveExploits0References2
CVE
CVE
•added 2026/08/13 3:00 p.m.•57 views

CVE-2026-73557

CVE-2026-73557 affects vLLM between 0.20.2rc0 and 0.26.0. The flaw arises in safe_load_prompt_embeds in vllm/renderers/embed_utils.py, where using torch.sparse.check_sparse_tensor_invariants with a process-global save/enable/restore state can be raced via concurrent prompt_embeds (POST /v1/chat/c...

6.3CVSS5.3AI score0.00404EPSS
SaveExploits0References4
attackerkb
attackerkb
•added 2026/08/13 3:00 p.m.•22 views

CVE-2026-73557

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

6.3CVSS5.3AI score0.00404EPSS
SaveExploits0References5Affected Software1
Vulnrichment
Vulnrichment
•added 2026/08/13 3:00 p.m.•10 views

CVE-2026-73557 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

6.3CVSS5.4AI score0.00404EPSS
SaveExploits0References4
Cvelist
Cvelist
•added 2026/08/13 3:00 p.m.•51 views

CVE-2026-73557 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

6.3CVSS0.00404EPSS
SaveExploits0References4
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/08/13 12:00 a.m.•0 views

CVE-2026-73557: Concurrent Execution using Shared Resource with Improper Synchronization

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

6.3CVSS5.8AI score0.00404EPSS
SaveExploits0References2
Rows per page
Query Builder