Commit aa2a1b8c authored by luopl's avatar luopl
Browse files

Update Qwen1.5-7b_single_dcu_inference.py

parent 7504ebd1
from vllm import LLM, SamplingParams from vllm import LLM, SamplingParams
# Sample prompts. # Sample prompts.
prompts = [ prompts = [
"The capital of France is", "The capital of France is",
] ]
# Create a sampling params object. # Create a sampling params object.
sampling_params = SamplingParams(temperature=0.8, top_p=0.95,top_k=50,stop="</s>") sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
# Create an LLM. # Create an LLM.
llm = LLM(model="./qwen2/Qwen1.5-7B-Chat",trust_remote_code=True,dtype="float16", enforce_eager=True) llm = LLM(model="./qwen2/Qwen1.5-7B-Chat",trust_remote_code=True,dtype="float16", enforce_eager=True)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment