zengrh3

Results 2 comments of zengrh3

@Oldpan @qism I met the same question as well while in my own Llama design. I passed the `eos_id` to the `runner.generate` function, but it still generates the token until...

@DarkLight1337 Hi, I noticed lots of progress in adding `input_embeds` in vLLM. So is that ready or not?