huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-25 02:42:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update peft + transformers + accelerate + bnb + safetensors (#1646)

Browse Source
This commit is contained in:
abhishek thakur 2024-03-15 13:23:26 +01:00 committed by Karol Damaszke
parent 7809825f0c
commit 86c5ce5aa5
5 changed files with 169 additions and 623 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Dockerfile
View File

@ -31,7 +31,7 @@ COPY launcher launcher
RUN cargo build --release RUN cargo build --release
# Text Generation Inference base image # Text Generation Inference base image
FROM vault.habana.ai/gaudi-docker/1.14.0/ubuntu22.04/habanalabs/pytorch-installer-2.1.1:latest as base FROM vault.habana.ai/gaudi-docker/1.15.0/ubuntu22.04/habanalabs/pytorch-installer-2.2.0:latest as base
# Text Generation Inference base env # Text Generation Inference base env
ENV HUGGINGFACE_HUB_CACHE=/data \ ENV HUGGINGFACE_HUB_CACHE=/data \
@ -58,7 +58,7 @@ COPY server/Makefile server/Makefile
RUN cd server && \ RUN cd server && \
make gen-server && \ make gen-server && \
pip install -r requirements.txt && \ pip install -r requirements.txt && \
pip install git+https://github.com/HabanaAI/DeepSpeed.git@1.14.0 && \ pip install git+https://github.com/HabanaAI/DeepSpeed.git@1.15.0 && \
pip install . --no-cache-dir pip install . --no-cache-dir
# Install benchmarker # Install benchmarker

4
server/Makefile
View File

@ -22,8 +22,8 @@ install-megablocks:
install: gen-server install: gen-server
pip install pip --upgrade pip install pip --upgrade
pip install -r requirements_cuda.txt pip install -r requirements.txt
pip install -e ".[bnb, accelerate, quantize, peft, outlines]" pip install -e "."
run-dev: run-dev:
SAFETENSORS_FAST_GPU=1 python -m torch.distributed.run --nproc_per_node=2 text_generation_server/cli.py serve bigscience/bloom-560m --sharded SAFETENSORS_FAST_GPU=1 python -m torch.distributed.run --nproc_per_node=2 text_generation_server/cli.py serve bigscience/bloom-560m --sharded

693
server/poetry.lock generated
View File

File diff suppressed because it is too large Load Diff

6
server/pyproject.toml
View File

@ -21,9 +21,9 @@ opentelemetry-exporter-otlp = "^1.15.0"
opentelemetry-instrumentation-grpc = "^0.36b0" opentelemetry-instrumentation-grpc = "^0.36b0"
hf-transfer = "^0.1.2" hf-transfer = "^0.1.2"
sentencepiece = "^0.1.97" sentencepiece = "^0.1.97"
peft = "^0.8.2" peft = "^0.9.0"
optimum-habana = "1.10.4" optimum-habana = "1.11.0"
transformers = "4.37.2" transformers = "4.38.2"
accelerate = "0.27.2" accelerate = "0.27.2"
outlines= { version = "^0.0.27", optional = true } outlines= { version = "^0.0.27", optional = true }

85
server/requirements.txt
View File

@ -1,40 +1,42 @@
accelerate==0.27.2 ; python_version >= "3.9" and python_version < "3.13" accelerate==0.27.2 ; python_version >= "3.9" and python_version < "3.13"
aiohttp==3.9.0 ; python_version >= "3.9" and python_version < "3.13" aiohttp==3.9.5 ; python_version >= "3.9" and python_version < "3.13"
aiosignal==1.3.1 ; python_version >= "3.9" and python_version < "3.13" aiosignal==1.3.1 ; python_version >= "3.9" and python_version < "3.13"
async-timeout==4.0.3 ; python_version >= "3.9" and python_version < "3.11" async-timeout==4.0.3 ; python_version >= "3.9" and python_version < "3.11"
attrs==23.1.0 ; python_version >= "3.9" and python_version < "3.13" attrs==23.2.0 ; python_version >= "3.9" and python_version < "3.13"
backoff==2.2.1 ; python_version >= "3.9" and python_version < "3.13" backoff==2.2.1 ; python_version >= "3.9" and python_version < "3.13"
certifi==2023.11.17 ; 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" 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" 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") colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_platform == "win32" or platform_system == "Windows")
coloredlogs==15.0.1 ; python_version >= "3.9" and python_version < "3.13" coloredlogs==15.0.1 ; python_version >= "3.9" and python_version < "3.13"
datasets==2.14.7 ; python_version >= "3.9" and python_version < "3.13" datasets==2.19.0 ; python_version >= "3.9" and python_version < "3.13"
deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13" deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13"
diffusers==0.26.3 ; python_version >= "3.9" and python_version < "3.13" diffusers==0.26.3 ; python_version >= "3.9" and python_version < "3.13"
dill==0.3.7 ; python_version >= "3.9" and python_version < "3.13" dill==0.3.8 ; python_version >= "3.9" and python_version < "3.13"
filelock==3.13.1 ; python_version >= "3.9" and python_version < "3.13" filelock==3.13.4 ; python_version >= "3.9" and python_version < "3.13"
frozenlist==1.4.0 ; python_version >= "3.9" and python_version < "3.13" frozenlist==1.4.1 ; python_version >= "3.9" and python_version < "3.13"
fsspec==2023.10.0 ; python_version >= "3.9" and python_version < "3.13" fsspec==2024.3.1 ; python_version >= "3.9" and python_version < "3.13"
fsspec[http]==2023.10.0 ; python_version >= "3.9" and python_version < "3.13" fsspec[http]==2024.3.1 ; python_version >= "3.9" and python_version < "3.13"
googleapis-common-protos==1.61.0 ; 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" grpc-interceptor==0.15.4 ; python_version >= "3.9" and python_version < "3.13"
grpcio-reflection==1.48.2 ; python_version >= "3.9" and python_version < "3.13" grpcio-reflection==1.48.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio-status==1.48.2 ; python_version >= "3.9" and python_version < "3.13" grpcio-status==1.48.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio==1.59.3 ; python_version >= "3.9" and python_version < "3.13" grpcio==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
hf-transfer==0.1.4 ; 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==0.20.3 ; python_version >= "3.9" and python_version < "3.13" huggingface-hub==0.22.2 ; python_version >= "3.9" and python_version < "3.13"
humanfriendly==10.0 ; python_version >= "3.9" and python_version < "3.13" humanfriendly==10.0 ; python_version >= "3.9" and python_version < "3.13"
idna==3.4 ; python_version >= "3.9" and python_version < "3.13" idna==3.7 ; python_version >= "3.9" and python_version < "3.13"
importlib-metadata==7.0.1 ; python_version >= "3.9" and python_version < "3.13" importlib-metadata==7.1.0 ; python_version >= "3.9" and python_version < "3.13"
jinja2==3.1.2 ; python_version >= "3.9" and python_version < "3.13" intel-openmp==2021.4.0 ; python_version >= "3.9" and python_version < "3.13" and platform_system == "Windows"
jinja2==3.1.3 ; python_version >= "3.9" and python_version < "3.13"
loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13" loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13"
markupsafe==2.1.3 ; python_version >= "3.9" and python_version < "3.13" markupsafe==2.1.5 ; python_version >= "3.9" and python_version < "3.13"
mkl==2021.4.0 ; python_version >= "3.9" and python_version < "3.13" and platform_system == "Windows"
mpmath==1.3.0 ; python_version >= "3.9" and python_version < "3.13" mpmath==1.3.0 ; python_version >= "3.9" and python_version < "3.13"
multidict==6.0.4 ; python_version >= "3.9" and python_version < "3.13" multidict==6.0.5 ; python_version >= "3.9" and python_version < "3.13"
multiprocess==0.70.15 ; python_version >= "3.9" and python_version < "3.13" multiprocess==0.70.16 ; python_version >= "3.9" and python_version < "3.13"
networkx==3.2.1 ; python_version >= "3.9" and python_version < "3.13" networkx==3.2.1 ; python_version >= "3.9" and python_version < "3.13"
numpy==1.26.2 ; 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-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-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-proto-http==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
@ -44,37 +46,38 @@ opentelemetry-instrumentation==0.36b0 ; python_version >= "3.9" and python_versi
opentelemetry-proto==1.15.0 ; 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-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" opentelemetry-semantic-conventions==0.36b0 ; python_version >= "3.9" and python_version < "3.13"
optimum-habana==1.10.4 ; python_version >= "3.9" and python_version < "3.13" optimum-habana==1.11.0 ; python_version >= "3.9" and python_version < "3.13"
optimum==1.17.1 ; python_version >= "3.9" and python_version < "3.13" optimum==1.19.1 ; python_version >= "3.9" and python_version < "3.13"
packaging==23.2 ; python_version >= "3.9" and python_version < "3.13" packaging==24.0 ; python_version >= "3.9" and python_version < "3.13"
pandas==2.1.3 ; python_version >= "3.9" and python_version < "3.13" pandas==2.2.2 ; python_version >= "3.9" and python_version < "3.13"
peft==0.4.0 ; python_version >= "3.9" and python_version < "3.13" peft==0.9.0 ; python_version >= "3.9" and python_version < "3.13"
pillow==10.1.0 ; python_version >= "3.9" and python_version < "3.13" pillow==10.3.0 ; python_version >= "3.9" and python_version < "3.13"
protobuf==3.20.3 ; python_version >= "3.9" and python_version < "3.13" protobuf==3.20.3 ; python_version >= "3.9" and python_version < "3.13"
psutil==5.9.6 ; python_version >= "3.9" and python_version < "3.13" psutil==5.9.8 ; python_version >= "3.9" and python_version < "3.13"
pyarrow-hotfix==0.6 ; python_version >= "3.9" and python_version < "3.13" pyarrow-hotfix==0.6 ; python_version >= "3.9" and python_version < "3.13"
pyarrow==14.0.1 ; python_version >= "3.9" and python_version < "3.13" pyarrow==16.0.0 ; python_version >= "3.9" and python_version < "3.13"
pyreadline3==3.4.1 ; sys_platform == "win32" and python_version >= "3.9" and python_version < "3.13" pyreadline3==3.4.1 ; sys_platform == "win32" and python_version >= "3.9" and python_version < "3.13"
python-dateutil==2.8.2 ; python_version >= "3.9" and python_version < "3.13" python-dateutil==2.9.0.post0 ; python_version >= "3.9" and python_version < "3.13"
pytz==2023.3.post1 ; python_version >= "3.9" and python_version < "3.13" pytz==2024.1 ; python_version >= "3.9" and python_version < "3.13"
pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13" pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13"
regex==2023.10.3 ; python_version >= "3.9" and python_version < "3.13" regex==2024.4.16 ; python_version >= "3.9" and python_version < "3.13"
requests==2.31.0 ; python_version >= "3.9" and python_version < "3.13" requests==2.31.0 ; python_version >= "3.9" and python_version < "3.13"
safetensors==0.4.2 ; python_version >= "3.9" and python_version < "3.13" safetensors==0.4.3 ; python_version >= "3.9" and python_version < "3.13"
sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13" sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13"
setuptools==69.0.2 ; python_version >= "3.9" and python_version < "3.13" setuptools==69.5.1 ; python_version >= "3.9" and python_version < "3.13"
six==1.16.0 ; python_version >= "3.9" and python_version < "3.13" six==1.16.0 ; python_version >= "3.9" and python_version < "3.13"
sympy==1.12 ; python_version >= "3.9" and python_version < "3.13" sympy==1.12 ; python_version >= "3.9" and python_version < "3.13"
tbb==2021.12.0 ; python_version >= "3.9" and python_version < "3.13" and platform_system == "Windows"
tokenizers==0.15.2 ; python_version >= "3.9" and python_version < "3.13" tokenizers==0.15.2 ; python_version >= "3.9" and python_version < "3.13"
tqdm==4.66.1 ; python_version >= "3.9" and python_version < "3.13" tqdm==4.66.2 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.37.2 ; python_version >= "3.9" and python_version < "3.13" transformers==4.38.2 ; python_version >= "3.9" and python_version < "3.13"
transformers[sentencepiece]==4.37.2 ; python_version >= "3.9" and python_version < "3.13" transformers[sentencepiece]==4.38.2 ; python_version >= "3.9" and python_version < "3.13"
typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13" typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.8.0 ; python_version >= "3.9" and python_version < "3.13" typing-extensions==4.11.0 ; python_version >= "3.9" and python_version < "3.13"
tzdata==2023.3 ; python_version >= "3.9" and python_version < "3.13" tzdata==2024.1 ; python_version >= "3.9" and python_version < "3.13"
urllib3==2.1.0 ; 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" 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" wrapt==1.16.0 ; python_version >= "3.9" and python_version < "3.13"
xxhash==3.4.1 ; python_version >= "3.9" and python_version < "3.13" xxhash==3.4.1 ; python_version >= "3.9" and python_version < "3.13"
yarl==1.9.3 ; python_version >= "3.9" and python_version < "3.13" yarl==1.9.4 ; python_version >= "3.9" and python_version < "3.13"
zipp==3.17.0 ; python_version >= "3.9" and python_version < "3.13" zipp==3.18.1 ; python_version >= "3.9" and python_version < "3.13"