1 matches found
GHSA-8WR5-JM2H-8R4F vLLM has Remote DoS via Invalid Recovered Token Reinjection
Summary A frontend-legal multi-request speculative workload can make vLLM produce an out-of-vocabulary recovered token equal to vocabsize, convert that value to -1 when choosing the next live token for a request, and then feed that -1 back into the next drafter input ids. On Qwen3 GPTQ this reach...