biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[ci] fix linter (#13701)

Browse Source 
Signed-off-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
youkaichao
2025-02-22 20:28:59 +08:00
committed by GitHub
parent 3e472d882a
commit 2382ad29d1
5 changed files with 11 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/offline_inference/data_parallel.py
View File

@@ -48,15 +48,16 @@ def main(dp_size, dp_rank, dp_master_ip, dp_master_port, GPUs_per_dp_rank):
max_tokens=16 * (dp_rank + 1))
# Create an LLM.
llm = LLM(model="facebook/opt-125m", tensor_parallel_size=2, enforce_eager=True)
llm = LLM(model="facebook/opt-125m",
tensor_parallel_size=2,
enforce_eager=True)
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(
f"DP rank {dp_rank}, Prompt: {prompt!r}, "
f"Generated text: {generated_text!r}")
print(f"DP rank {dp_rank}, Prompt: {prompt!r}, "
f"Generated text: {generated_text!r}")
if __name__ == "__main__":