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

precommit

Browse source
This commit is contained in:
Xi Yan 2024-11-08 17:58:58 -08:00
parent 1ebf6447c5
commit ba82021d4b
11 changed files with 19 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/inline/inference/meta_reference/quantization/loader.py
View file

@ -21,13 +21,13 @@ from llama_models.llama3.api.args import ModelArgs
from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock
from llama_models.sku_list import resolve_model
from llama_stack.apis.inference import QuantizationType
from termcolor import cprint
from torch import nn, Tensor
from torchao.quantization.GPTQ import Int8DynActInt4WeightLinear
from llama_stack.apis.inference import QuantizationType
from ..config import MetaReferenceQuantizedInferenceConfig