Lucene search
+L

13 matches found

Veracode
Veracode
•added 2026/10/29 5:20 a.m.•25 views

VLLM: Out-of-vocabulary Prompt Token Id Passes Input Validation And Triggers A CUDA Device-side Assert (engine Crash / D

For a model whose vocabulary size is an exact multiple of the embedding padding size 64 — e.g. any Llama-2-family model, vocab 32000 — a single request carrying a pre-tokenized prompt with token id equal to the vocab size 32000 passes vLLM's input-id validation but is one past the last embedding...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References4Affected Software1
SUSE CVE
SUSE CVE
•added 2026/09/23 12:13 a.m.•18 views

SUSE CVE-2026-94626

vLLM through 0.29.0 fails to validate the tpsize parameter in kvtransferparams on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tpsize values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel...

8.7CVSS7.4AI score0.00627EPSS
SaveExploits0References3
RedhatCVE
RedhatCVE
•added 2026/09/22 6:56 p.m.•18 views

CVE-2026-94626

A flaw was found in vLLM. A remote attacker can exploit a vulnerability in the kvtransferparams function on OpenAI-compatible completion endpoints by supplying an unvalidated tpsize parameter. This allows for unbounded memory allocation, leading to memory exhaustion and a kernel Out-Of-Memory OOM...

8.7CVSS7.2AI score0.00627EPSS
SaveExploits0References8
EUVD
EUVD
•added 2026/09/22 12:30 a.m.•20 views

EUVD-2026-84220

vLLM through 0.29.0 fails to validate the tpsize parameter in kvtransferparams on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tpsize values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel...

8.7CVSS7.4AI score0.00627EPSS
SaveExploits0References6
Snyk
Snyk
•added 2026/09/21 11:22 p.m.•62 views

Memory Allocation with Excessive Size Value

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Memory Allocation with Excessive Size Value via the tpsize parameter in kvtransferparams on OpenAI-compatible completion endpoints, which is not...

8.7CVSS7.3AI score0.00627EPSS
SaveExploits0References2
NVD
NVD
•added 2026/09/21 10:17 p.m.•21 views

CVE-2026-94626

vLLM through 0.29.0 fails to validate the tpsize parameter in kvtransferparams on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tpsize values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel...

8.7CVSS0.00627EPSS
SaveExploits0References5
PyPA
PyPA
•added 2026/09/21 10:17 p.m.•72 views

PYSEC-2026-4008

vLLM through 0.29.0 fails to validate the tpsize parameter in kvtransferparams on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tpsize values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel...

8.7CVSS7.4AI score0.00627EPSS
SaveExploits0References5Affected Software1
osv_pysec
osv_pysec
•added 2026/09/21 10:17 p.m.•32 views

PYSEC-2026-4008

vLLM through 0.29.0 fails to validate the tpsize parameter in kvtransferparams on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tpsize values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel...

8.7CVSS7.4AI score0.00627EPSS
SaveExploits0References5
osv_cve
osv_cve
•added 2026/09/21 10:04 p.m.•47 views

CVE-2026-94626 vLLM through 0.29.0 Memory Exhaustion via Unvalidated NIXL tp_size

vLLM through 0.29.0 fails to validate the tpsize parameter in kvtransferparams on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tpsize values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel...

8.7CVSS7.4AI score0.00627EPSS
SaveExploits0References7
CVE
CVE
•added 2026/09/21 10:04 p.m.•70 views

CVE-2026-94626

vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints. In prefill/decode disaggregated deployments using NIXL, an unauthenticated remote attacker can supply an arbitrary tp_size value to allocate unbounded memory , ultimately t...

8.7CVSS7.4AI score0.00627EPSS
SaveExploits0References5Affected Software1
Mend
Mend
•added 2026/09/21 10:04 p.m.•15 views

CVE-2026-94626

vLLM through 0.29.0 fails to validate the tpsize parameter in kvtransferparams on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tpsize values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel...

8.7CVSS7.4AI score0.00627EPSS
SaveExploits0References7
Cvelist
Cvelist
•added 2026/09/21 10:04 p.m.•57 views

CVE-2026-94626 vLLM through 0.29.0 Memory Exhaustion via Unvalidated NIXL tp_size

vLLM through 0.29.0 fails to validate the tpsize parameter in kvtransferparams on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tpsize values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel...

8.7CVSS0.00627EPSS
SaveExploits0References5
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/21 12:00 a.m.•13 views

CVE-2026-94626: Memory Allocation with Excessive Size Value

vLLM through 0.29.0 fails to validate the tpsize parameter in kvtransferparams on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tpsize values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel...

8.7CVSS7.5AI score0.00627EPSS
SaveExploits0References4
Rows per page
Query Builder