KBaba7/llama.cpp

1# llama.cpp/example/batched2 3The example demonstrates batched generation from a given prompt4 5```bash6./llama-batched -m ./models/llama-7b-v2/ggml-model-f16.gguf -p "Hello my name is" -np 47 8...9 10main: n_len = 32, n_ctx = 2048, n_parallel = 4, n_kv_req = 11311 12 Hello my name is13 14main: generating 4 sequences ...15 16main: stream 0 finished17main: stream 1 finished18main: stream 2 finished19main: stream 3 finished20 21sequence 0:22 23Hello my name is Shirley. I am a 25-year-old female who has been working for over 5 years as a b24 25sequence 1:26 27Hello my name is Renee and I'm a 32 year old female from the United States. I'm looking for a man between28 29sequence 2:30 31Hello my name is Diana. I am looking for a housekeeping job. I have experience with children and have my own transportation. I am32 33sequence 3:34 35Hello my name is Cody. I am a 3 year old neutered male. I am a very friendly cat. I am very playful and36 37main: decoded 108 tokens in 3.57 s, speed: 30.26 t/s38 39llama_print_timings:        load time =   587.00 ms40llama_print_timings:      sample time =     2.56 ms /   112 runs   (    0.02 ms per token, 43664.72 tokens per second)41llama_print_timings: prompt eval time =  4089.11 ms /   118 tokens (   34.65 ms per token,    28.86 tokens per second)42llama_print_timings:        eval time =     0.00 ms /     1 runs   (    0.00 ms per token,      inf tokens per second)43llama_print_timings:       total time =  4156.04 ms44```45