phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

pre-commit lint

Browse source
This commit is contained in:
Xi Yan 2024-09-28 16:04:41 -07:00
parent ced5fb6388
commit 4ae8c63a2b
9 changed files with 19 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/impls/meta_reference/inference/quantization/loader.py
View file

@ -14,6 +14,10 @@ import torch
from fairscale.nn.model_parallel.mappings import reduce_from_model_parallel_region
from llama_models.llama3.api.model import Transformer, TransformerBlock
from termcolor import cprint
from torch import Tensor
from llama_stack.apis.inference import QuantizationType
from llama_stack.apis.inference.config import (
@ -21,9 +25,6 @@ from llama_stack.apis.inference.config import (
MetaReferenceImplConfig,
)
from termcolor import cprint
from torch import Tensor
def is_fbgemm_available() -> bool:
try: