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

Refactor system architecture (#82)

Browse Source
This commit is contained in:
Woosuk Kwon
2023-05-09 15:30:12 -07:00
committed by GitHub
parent 8917782af6
commit 7c041ab578
40 changed files with 194 additions and 446 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
cacheflow/model_executor/models/__init__.py Normal file
View File

@@ -0,0 +1,12 @@
from cacheflow.model_executor.models.gpt_neox import GPTNeoXForCausalLM
from cacheflow.model_executor.models.gpt2 import GPT2LMHeadModel
from cacheflow.model_executor.models.llama import LlamaForCausalLM
from cacheflow.model_executor.models.opt import OPTForCausalLM
__all__ = [
"GPT2LMHeadModel",
"GPTNeoXForCausalLM",
"LlamaForCausalLM",
"OPTForCausalLM",
]