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

reable xpu, broken by gptq and setuptool upgrade

Browse Source 
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
This commit is contained in:
Wang, Yi A 2024-05-31 07:52:31 -07:00
parent 967ced2ff4
commit 9c722a4e35
3 changed files with 51 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Dockerfile_intel
View File

@ -66,7 +66,7 @@ COPY server server
COPY server/Makefile server/Makefile COPY server/Makefile server/Makefile
RUN cd server && \ RUN cd server && \
make gen-server && \ make gen-server && \
pip install -r requirements_cuda.txt && \ pip install -r requirements_intel.txt && \
pip install ".[accelerate, peft, outlines]" --no-cache-dir pip install ".[accelerate, peft, outlines]" --no-cache-dir
ENV CCL_ROOT=/opt/intel/oneapi/ccl/latest ENV CCL_ROOT=/opt/intel/oneapi/ccl/latest

48
server/requirements_intel.txt Normal file
View File

@ -0,0 +1,48 @@
backoff==2.2.1 ; python_version >= "3.9" and python_version < "3.13"
certifi==2024.2.2 ; python_version >= "3.9" and python_version < "3.13"
charset-normalizer==3.3.2 ; python_version >= "3.9" and python_version < "3.13"
click==8.1.7 ; python_version >= "3.9" and python_version < "3.13"
colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_platform == "win32" or platform_system == "Windows")
deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13"
einops==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
filelock==3.14.0 ; python_version >= "3.9" and python_version < "3.13"
fsspec==2024.5.0 ; python_version >= "3.9" and python_version < "3.13"
googleapis-common-protos==1.63.0 ; python_version >= "3.9" and python_version < "3.13"
grpc-interceptor==0.15.4 ; python_version >= "3.9" and python_version < "3.13"
grpcio-reflection==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio-status==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio==1.64.0 ; python_version >= "3.9" and python_version < "3.13"
hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13"
huggingface-hub==0.23.1 ; python_version >= "3.9" and python_version < "3.13"
idna==3.7 ; python_version >= "3.9" and python_version < "3.13"
loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13"
numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-api==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-grpc==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-http==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-instrumentation-grpc==0.36b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-instrumentation==0.36b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-proto==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-sdk==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-semantic-conventions==0.36b0 ; python_version >= "3.9" and python_version < "3.13"
packaging==24.0 ; python_version >= "3.9" and python_version < "3.13"
pillow==10.3.0 ; python_version >= "3.9" and python_version < "3.13"
prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
protobuf==4.25.3 ; python_version >= "3.9" and python_version < "3.13"
py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13"
regex==2024.5.15 ; python_version >= "3.9" and python_version < "3.13"
requests==2.32.2 ; python_version >= "3.9" and python_version < "3.13"
safetensors==0.4.3 ; python_version >= "3.9" and python_version < "3.13"
scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13"
setuptools==69.5.1 ; python_version >= "3.9" and python_version < "3.13"
tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13"
tqdm==4.66.4 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.41.1 ; python_version >= "3.9" and python_version < "3.13"
typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.12.0 ; python_version >= "3.9" and python_version < "3.13"
urllib3==2.2.1 ; python_version >= "3.9" and python_version < "3.13"
win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
wrapt==1.16.0 ; python_version >= "3.9" and python_version < "3.13"

4
server/text_generation_server/layers/gptq/__init__.py
View File

@ -57,5 +57,5 @@ elif CAN_EXLLAMA:
except ImportError: except ImportError:
pass pass
if SYSTEM != "xpu":
from text_generation_server.layers.gptq.quant_linear import QuantLinear from text_generation_server.layers.gptq.quant_linear import QuantLinear