Lucene search
+L

7 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
Github Security Blog
Github Security Blog
•added 2026/10/28 9:15 p.m.•33 views

vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

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
SaveExploits0References6Affected Software1
osv_ghsa
osv_ghsa
•added 2026/10/28 9:15 p.m.•19 views

GHSA-Q97C-P368-75C4 vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

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
SaveExploits0References6
Vulnrichment
Vulnrichment
•added 2026/10/26 5:18 p.m.•8 views

CVE-2026-115916 vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes maxtokenid with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References4
osv_cve
osv_cve
•added 2026/10/26 5:18 p.m.•23 views

CVE-2026-115916 vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes maxtokenid with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References6
Cvelist
Cvelist
•added 2026/10/26 5:18 p.m.•39 views

CVE-2026-115916 vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes maxtokenid with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact...

6.5CVSS0.00312EPSS
SaveExploits0References4
CVE
CVE
•added 2026/10/26 5:18 p.m.•65 views

CVE-2026-115916

The vLLM inference and serving engine (versions prior to 0.32.0 ) is vulnerable to a Denial of Service (DoS) due to an off-by-one error in vllm/tokenizers/hf.py. The max_token_id is calculated with an incorrect upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to bypass...

6.5CVSS6AI score0.00312EPSS
SaveExploits0References4Affected Software1
Rows per page
Query Builder