huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-06-13 12:52:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(neuron): use new cache import path

Browse Source
This commit is contained in:
David Corvoysier 2025-05-23 08:37:17 +00:00
parent d4523f290a
commit 0f52049e25
3 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
backends/neuron/server/text_generation_server/model.py
View File

@ -9,7 +9,7 @@ from loguru import logger
from transformers import AutoConfig from transformers import AutoConfig
from optimum.neuron import NeuronModelForCausalLM from optimum.neuron import NeuronModelForCausalLM
from optimum.neuron.utils import get_hub_cached_entries from optimum.neuron.cache import get_hub_cached_entries
def get_export_kwargs_from_env(): def get_export_kwargs_from_env():

2
backends/neuron/tests/fixtures/model.py vendored
View File

@ -9,7 +9,7 @@ import pytest
from transformers import AutoTokenizer from transformers import AutoTokenizer
from optimum.neuron import NeuronModelForCausalLM from optimum.neuron import NeuronModelForCausalLM
from optimum.neuron.utils import synchronize_hub_cache from optimum.neuron.cache import synchronize_hub_cache
from optimum.neuron.version import __sdk_version__ as sdk_version from optimum.neuron.version import __sdk_version__ as sdk_version
from optimum.neuron.version import __version__ as version from optimum.neuron.version import __version__ as version

2
backends/neuron/tgi_env.py
View File

@ -10,7 +10,7 @@ from huggingface_hub import constants
from transformers import AutoConfig from transformers import AutoConfig
from optimum.neuron.modeling_decoder import get_available_cores from optimum.neuron.modeling_decoder import get_available_cores
from optimum.neuron.utils import get_hub_cached_entries from optimum.neuron.cache import get_hub_cached_entries
from optimum.neuron.utils.version_utils import get_neuronxcc_version from optimum.neuron.utils.version_utils import get_neuronxcc_version