vLLM says its serving software now supports Ling-3.1-flash from day one. The model has about 560 billion total parameters, around 25 billion active per token an
vLLM says its serving software now supports Ling-3.1-flash from day one. The model has about 560 billion total parameters, around 25 billion active per token and a context window of up to one million tokens, according to vLLM. Why it matter
Open discussion →