mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-12-15 19:30:36 +08:00
support batch infer in vllm
This commit is contained in:
@@ -1,2 +1,3 @@
|
||||
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
|
||||
template: llama3
|
||||
infer_backend: huggingface # choices: [huggingface, vllm]
|
||||
|
||||
Reference in New Issue
Block a user