31 matches found
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...
EUVD-2026-110036
vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert engine crash / DoS...
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...
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...
SUSE CVE-2026-115916
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...
PYSEC-2026-4347
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...
CVE-2026-115916
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...
PYSEC-2026-4347
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...
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...
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...
CVE-2026-115916
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...
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...
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...
PT-2026-123448
Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.32.0 Description An off-by-one error in the calculation of max token id within vllm/tokenizers/hf.py allows a pre-tokenized prompt ID equal to the vocabulary size to pass validation. When the tensor-parallel size is on...
PT-2026-132750
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max token id 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...
CVE-2026-100654
vLLM versions before 0.29.0 are vulnerable to a Denial of Service (DoS) attack. The issue arises because the POST /v1/completions and POST /v1/chat/completions endpoints accept user-controlled stop_token_ids but fail to verify if these IDs fall within the model's vocabulary/logits range. When min...
CVE-2026-93592
A flaw was found in vLLM. An unauthenticated attacker can exploit an input validation vulnerability by submitting negative token IDs to the /v1/embeddings and /pooling endpoints. This action triggers a CUDA device-side assertion, which poisons the GPU context and causes the engine to crash...
SUSE CVE-2026-93592
vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative token IDs. A single request with a negative token ID triggers a CUDA device-side assertion that...
PYSEC-2026-3997
vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative token IDs. A single request with a negative token ID triggers a CUDA device-side assertion that...
PYSEC-2026-3997
vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative token IDs. A single request with a negative token ID triggers a CUDA device-side assertion that...