13 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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...