support batch infer in vllm

This commit is contained in:
hiyouga
2024-12-04 13:50:00 +00:00
parent dc78355002
commit 1324d158f9
29 changed files with 148 additions and 407 deletions

View File

@@ -1,2 +1,3 @@
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
template: llama3
infer_backend: huggingface # choices: [huggingface, vllm]