huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Simplify two ipex conditions

Browse Source
This commit is contained in:
Daniël de Kok 2024-11-18 16:18:59 +00:00
parent a5ecd6e586
commit c6393c5512
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
server/text_generation_server/layers/moe/unquantized.py
View File

@ -8,10 +8,10 @@ from text_generation_server.utils.weights import UnquantizedWeight, Weights
if SYSTEM == "rocm":
from vllm.model_executor.layers.fused_moe import fused_moe
elif SYSTEM != "ipex":
from moe_kernels.fused_moe import fused_moe
else:
elif SYSTEM == "ipex":
from intel_extension_for_pytorch.llm.modules import GatedMLPMOE
else:
from moe_kernels.fused_moe import fused_moe
class UnquantizedSparseMoELayer(nn.Module):

6
server/text_generation_server/models/custom_modeling/flash_dbrx_modeling.py
View File

@ -25,10 +25,10 @@ from text_generation_server.utils.import_utils import SYSTEM
if SYSTEM == "rocm":
from vllm.model_executor.layers.fused_moe import fused_moe
elif SYSTEM != "ipex":
from moe_kernels.fused_moe import fused_moe
else:
elif SYSTEM == "ipex":
from intel_extension_for_pytorch.llm.modules import GatedMLPMOE
else:
from moe_kernels.fused_moe import fused_moe
from text_generation_server.layers.attention import (
paged_attention,