vllm

vLLM before 0.29.0 Heap Overflow DoS via IAMF Audio Transcription Upload

vllm-project vLLM Penalty utils.py get_token_bin_counts_and_mask denial of service

vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

vLLM: Unbounded Prometheus label cardinality from attacker-controlled HTTP method tokens in the vLLM Rust frontend metrics middleware (unauthenticated denial of service)

vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach

vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites)

vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`

vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features

vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core