Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Apply suggestions from code review 

Co-authored-by: Daniël de Kok <me@github.danieldk.eu>
This commit is contained in:
Wang, Yi 2024-11-18 19:28:07 +08:00 committed by GitHub
parent e0e39fa0d9
commit 53b6f6e604
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
Dockerfile_intel
View File

@ -83,12 +83,7 @@ RUN wget -qO - https://repositories.intel.com/gpu/intel-graphics.key | gpg --dea
RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB \
| gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list
RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB \
| gpg --dearmor > /tmp/intel-for-pytorch-gpu-dev-keyring.gpg
RUN mv /tmp/intel-for-pytorch-gpu-dev-keyring.gpg /usr/share/keyrings
RUN echo "deb [signed-by=/usr/share/keyrings/intel-for-pytorch-gpu-dev-keyring.gpg] https://apt.repos.intel.com/intel-for-pytorch-gpu-dev all main" > /tmp/intel-for-pytorch-gpu-dev.list
RUN echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/intel-for-pytorch-gpu-dev all main" > /tmp/intel-for-pytorch-gpu-dev.list
RUN mv /tmp/intel-for-pytorch-gpu-dev.list /etc/apt/sources.list.d

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

@ -27,10 +27,10 @@ from text_generation_server.utils.weights import (
if SYSTEM == "rocm":
from .fused_moe_rocm import grouped_topk
from vllm.model_executor.layers.fused_moe import fused_topk
elif SYSTEM != "ipex":
from moe_kernels.fused_moe import fused_topk, grouped_topk
else:
elif SYSTEM == "ipex":
from intel_extension_for_pytorch.llm.modules import GatedMLPMOE
else:
from moe_kernels.fused_moe import fused_topk, grouped_topk
# NOTE: we are using a protocol here, because multiple inherance is not nice.