phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 22:19:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix a couple dangling imports

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-07 12:54:58 -08:00
parent 0747ee2f10
commit ec603a435a
2 changed files with 2 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/inline/inference/meta_reference/quantization/loader.py
View file

@ -23,14 +23,13 @@ from llama_models.sku_list import resolve_model
from llama_stack.apis.inference import QuantizationType
from llama_stack.providers.inline.meta_reference.inference.config import (
MetaReferenceQuantizedInferenceConfig,
)
from termcolor import cprint
from torch import nn, Tensor
from torchao.quantization.GPTQ import Int8DynActInt4WeightLinear
from ..config import MetaReferenceQuantizedInferenceConfig
def swiglu_wrapper(
self,