run

#2
by rakmik - opened

how run it in wsl win 10

pip install git+https://github.com/snowflake-labs/vllm.git@swiftkv

from vllm import LLM
llm = LLM(model="Snowflake/Llama-3.1-SwiftKV-8B-Instruct-FP8")

from vllm import SamplingParams
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)

prompts = ["Your prompt here"]
outputs = llm.generate(prompts, sampling_params)
for output in outputs:
print(output.outputs[0].text)

not run

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment