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

Use runtime profiling to replace manual memory analyzers (#81)

Browse Source
This commit is contained in:
Zhuohan Li
2023-05-19 11:35:44 -06:00
committed by GitHub
parent 825d8892b5
commit f756799b84
14 changed files with 211 additions and 478 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
cacheflow/model_executor/__init__.py
View File

@@ -1,11 +1,12 @@
from cacheflow.model_executor.input_metadata import InputMetadata
from cacheflow.model_executor.model_loader import get_model, get_memory_analyzer
from cacheflow.model_executor.utils import set_random_seed
from cacheflow.model_executor.model_loader import get_model
from cacheflow.model_executor.utils import (set_random_seed,
get_cache_block_size)
__all__ = [
"InputMetadata",
"get_cache_block_size",
"get_model",
"get_memory_analyzer",
"set_random_seed",
]