PT-2026-102786

vLLM through 0.29.0 fails to properly validate bad words token indices against the model's generation output width in SamplingParams.update from tokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests...

PT-2026-95873

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.29.1 Description The software fails to properly validate bad words token indices against the model's generation output width within the SamplingParams.update from tokenizer function. This allows attackers to provide...