CVE-2026-94624

A flaw was found in vLLM. A remote attacker can exploit a denial of service vulnerability in the P2P KV offloading mechanism. By supplying arbitrary remote host and port values, an attacker can create unreachable peer sessions that consume ZeroMQ sockets. This resource exhaustion leads to an...

CVE-2026-94622

A flaw was found in vLLM. A remote attacker can exploit this vulnerability by sending requests with incomplete kvtransferparams dictionary entries to the NIXL connector's metadata handling. This can trigger an uncaught error in the EngineCore scheduling, leading to the termination of the decode...

EUVD-2026-84216

vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for prefill/decode disaggregated deployments. Attackers can send requests with incomplete kvtransferparams dictionary entries to trigger an uncaught KeyError in EngineCore scheduling,...

EUVD-2026-84218

vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can supply arbitrary remote host and port values in kvtransferparams to create unreachable peer sessio...

CVE-2026-94624

vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can supply arbitrary remote host and port values in kvtransferparams to create unreachable peer sessio...

CVE-2026-94622

vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for prefill/decode disaggregated deployments. Attackers can send requests with incomplete kvtransferparams dictionary entries to trigger an uncaught KeyError in EngineCore scheduling,...

CVE-2026-94624

vLLM through version 0.29.0 contains a denial-of-service vulnerability in its P2P KV offloading subsystem. When the OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier, an unauthenticated remote attacker can supply arbitrary host and port values via kv_t...

CVE-2026-94624 vLLM through 0.29.0 Denial of Service via Unbounded P2P KV Offloading Sessions

vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can supply arbitrary remote host and port values in kvtransferparams to create unreachable peer sessio...

CVE-2026-94624 vLLM through 0.29.0 Denial of Service via Unbounded P2P KV Offloading Sessions

vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can supply arbitrary remote host and port values in kvtransferparams to create unreachable peer sessio...

CVE-2026-94622

vLLM versions through 0.29.0 are affected by a denial of service vulnerability in the NIXL connector's metadata handling, specifically affecting prefill/decode disaggregated deployments. An unauthenticated, remote attacker can send requests with incomplete kv_transfer_params dictionary entries to...

CVE-2026-94622 vLLM through 0.29.0 Denial of Service via Incomplete NIXL KV Transfer Metadata

vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for prefill/decode disaggregated deployments. Attackers can send requests with incomplete kvtransferparams dictionary entries to trigger an uncaught KeyError in EngineCore scheduling,...

SUSE CVE-2026-44223

vLLM is an inference and serving engine for large language models LLMs. From 0.18.0 to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The...

CVE-2026-55514

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...