huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-21 23:02:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Upgrade to SynapseAI 1.18 (#227)

Browse Source 
Signed-off-by: yuanwu <yuan.wu@intel.com>
Co-authored-by: Thanaji Rao Thakkalapelli <tthakkalapelli@habana.ai>
This commit is contained in:
yuanwu2017 2024-11-01 03:14:44 +08:00 committed by GitHub
parent 7fb4af9a87
commit 8d84ffabf2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 1408 additions and 1273 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Dockerfile
View File

@ -32,7 +32,7 @@ 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/1.17.0/ubuntu22.04/habanalabs/pytorch-installer-2.3.1:latest as base FROM vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest as base
# Text Generation Inference base env # Text Generation Inference base env
ENV HUGGINGFACE_HUB_CACHE=/data \ ENV HUGGINGFACE_HUB_CACHE=/data \
@ -61,7 +61,7 @@ RUN cd server && \
make gen-server && \ make gen-server && \
pip install -r requirements.txt && \ pip install -r requirements.txt && \
bash ./dill-0.3.8-patch.sh && \ bash ./dill-0.3.8-patch.sh && \
pip install git+https://github.com/HabanaAI/DeepSpeed.git@1.17.0 && \ pip install git+https://github.com/HabanaAI/DeepSpeed.git@1.18.0 && \
BUILD_CUDA_EXT=0 pip install git+https://github.com/AutoGPTQ/AutoGPTQ.git@097dd04e --no-build-isolation && \ BUILD_CUDA_EXT=0 pip install git+https://github.com/AutoGPTQ/AutoGPTQ.git@097dd04e --no-build-isolation && \
pip install . --no-cache-dir pip install . --no-cache-dir

11
examples/run_generation.py
View File

@ -31,13 +31,18 @@ def get_args():
parser.add_argument( parser.add_argument(
"--max_concurrent_requests", type=int, default=256, help="Max number of concurrent requests" "--max_concurrent_requests", type=int, default=256, help="Max number of concurrent requests"
) )
parser.add_argument(
"--seed", type=int, default=42, help="Random seed for datasets"
)
return parser.parse_args() return parser.parse_args()
def read_dataset( def read_dataset(
max_input_length: int, max_input_length: int,
total_sample_count: int, total_sample_count: int,
model_id: str model_id: str,
seed: int,
) -> List[str]: ) -> List[str]:
""" """
Loads public dataset from HF: https://huggingface.co/datasets/DIBT/10k_prompts_ranked Loads public dataset from HF: https://huggingface.co/datasets/DIBT/10k_prompts_ranked
@ -51,7 +56,7 @@ def read_dataset(
) )
if len(dataset) > total_sample_count: if len(dataset) > total_sample_count:
dataset = dataset.select(range(total_sample_count)) dataset = dataset.select(range(total_sample_count))
dataset = dataset.shuffle() dataset = dataset.shuffle(seed=seed)
return [sample["prompt"] for sample in dataset] return [sample["prompt"] for sample in dataset]
@ -71,7 +76,7 @@ def is_tgi_available(
def main(): def main():
args = get_args() args = get_args()
dataset = read_dataset( dataset = read_dataset(
args.max_input_length, args.total_sample_count, args.model_id args.max_input_length, args.total_sample_count, args.model_id, args.seed
) )
if not is_tgi_available(args.server_address): if not is_tgi_available(args.server_address):

2594
server/poetry.lock generated
View File

File diff suppressed because it is too large Load Diff

4
server/pyproject.toml
View File

@ -22,8 +22,8 @@ opentelemetry-instrumentation-grpc = "^0.36b0"
hf-transfer = "^0.1.2" hf-transfer = "^0.1.2"
sentencepiece = "^0.1.97" sentencepiece = "^0.1.97"
peft = "^0.10" peft = "^0.10"
optimum-habana = "1.13.2" optimum-habana = "1.14.1"
transformers = "4.43.4" transformers = "4.45.2"
numpy = "1.26.4" numpy = "1.26.4"
accelerate = "0.33.0" accelerate = "0.33.0"
outlines= { version = "^0.0.36", optional = true } outlines= { version = "^0.0.36", optional = true }

68
server/requirements.txt
View File

@ -1,40 +1,40 @@
accelerate==0.33.0 ; python_version >= "3.9" and python_version < "3.13" accelerate==0.33.0 ; python_version >= "3.9" and python_version < "3.13"
aiohappyeyeballs==2.4.0 ; python_version >= "3.9" and python_version < "3.13" aiohappyeyeballs==2.4.3 ; python_version >= "3.9" and python_version < "3.13"
aiohttp==3.10.5 ; python_version >= "3.9" and python_version < "3.13" aiohttp==3.10.10 ; 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==24.2.0 ; python_version >= "3.9" and python_version < "3.13" attrs==24.2.0 ; 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==2024.7.4 ; python_version >= "3.9" and python_version < "3.13" certifi==2024.8.30 ; 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==3.4.0 ; 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==2.21.0 ; python_version >= "3.9" and python_version < "3.13" datasets==3.0.1 ; 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==0.29.2 ; python_version >= "3.9" and python_version < "3.13" diffusers==0.29.2 ; python_version >= "3.9" and python_version < "3.13"
dill==0.3.8 ; python_version >= "3.9" and python_version < "3.13" dill==0.3.7 ; python_version >= "3.9" and python_version < "3.13"
filelock==3.15.4 ; python_version >= "3.9" and python_version < "3.13" filelock==3.16.1 ; python_version >= "3.9" and python_version < "3.13"
frozenlist==1.4.1 ; python_version >= "3.9" and python_version < "3.13" frozenlist==1.4.1 ; python_version >= "3.9" and python_version < "3.13"
fsspec==2024.6.1 ; python_version >= "3.9" and python_version < "3.13" fsspec==2024.6.1 ; python_version >= "3.9" and python_version < "3.13"
fsspec[http]==2024.6.1 ; python_version >= "3.9" and python_version < "3.13" fsspec[http]==2024.6.1 ; python_version >= "3.9" and python_version < "3.13"
googleapis-common-protos==1.63.2 ; python_version >= "3.9" and python_version < "3.13" googleapis-common-protos==1.65.0 ; 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==1.66.0 ; python_version >= "3.9" and python_version < "3.13" grpcio==1.67.0 ; python_version >= "3.9" and python_version < "3.13"
hf-transfer==0.1.8 ; python_version >= "3.9" and python_version < "3.13" hf-transfer==0.1.8 ; python_version >= "3.9" and python_version < "3.13"
huggingface-hub==0.24.6 ; python_version >= "3.9" and python_version < "3.13" huggingface-hub==0.26.1 ; 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==3.8 ; python_version >= "3.9" and python_version < "3.13" idna==3.10 ; python_version >= "3.9" and python_version < "3.13"
importlib-metadata==8.4.0 ; python_version >= "3.9" and python_version < "3.13" importlib-metadata==8.5.0 ; python_version >= "3.9" and python_version < "3.13"
jinja2==3.1.4 ; python_version >= "3.9" and python_version < "3.13" jinja2==3.1.4 ; python_version >= "3.9" and python_version < "3.13"
joblib==1.4.2 ; python_version >= "3.9" and python_version < "3.13" joblib==1.4.2 ; 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==2.1.5 ; python_version >= "3.9" and python_version < "3.13" markupsafe==3.0.2 ; python_version >= "3.9" and python_version < "3.13"
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==6.0.5 ; python_version >= "3.9" and python_version < "3.13" multidict==6.1.0 ; python_version >= "3.9" and python_version < "3.13"
multiprocess==0.70.16 ; python_version >= "3.9" and python_version < "3.13" multiprocess==0.70.15 ; 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==1.26.4 ; 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"
@ -46,43 +46,45 @@ 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==1.13.2 ; python_version >= "3.9" and python_version < "3.13" optimum-habana==1.14.1 ; python_version >= "3.9" and python_version < "3.13"
optimum==1.21.4 ; python_version >= "3.9" and python_version < "3.13" optimum==1.23.2 ; python_version >= "3.9" and python_version < "3.13"
packaging==24.1 ; python_version >= "3.9" and python_version < "3.13" packaging==24.1 ; python_version >= "3.9" and python_version < "3.13"
pandas==2.2.2 ; python_version >= "3.9" and python_version < "3.13" pandas==2.2.3 ; python_version >= "3.9" and python_version < "3.13"
peft==0.10.0 ; python_version >= "3.9" and python_version < "3.13" peft==0.10.0 ; python_version >= "3.9" and python_version < "3.13"
pillow==10.4.0 ; python_version >= "3.9" and python_version < "3.13" pillow==11.0.0 ; python_version >= "3.9" and python_version < "3.13"
prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13" prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
propcache==0.2.0 ; 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==6.0.0 ; python_version >= "3.9" and python_version < "3.13" psutil==6.1.0 ; python_version >= "3.9" and python_version < "3.13"
py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13" py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
pyarrow==17.0.0 ; python_version >= "3.9" and python_version < "3.13" pyarrow==17.0.0 ; 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==3.5.4 ; sys_platform == "win32" and python_version >= "3.9" and python_version < "3.13"
python-dateutil==2.9.0.post0 ; 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==2024.1 ; python_version >= "3.9" and python_version < "3.13" pytz==2024.2 ; python_version >= "3.9" and python_version < "3.13"
pyyaml==6.0.2 ; python_version >= "3.9" and python_version < "3.13" pyyaml==6.0.2 ; python_version >= "3.9" and python_version < "3.13"
regex==2024.7.24 ; python_version >= "3.9" and python_version < "3.13" regex==2024.9.11 ; python_version >= "3.9" and python_version < "3.13"
requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13" requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13"
safetensors==0.4.4 ; python_version >= "3.9" and python_version < "3.13" safetensors==0.4.5 ; python_version >= "3.9" and python_version < "3.13"
scikit-learn==1.5.1 ; python_version >= "3.9" and python_version < "3.13" scikit-learn==1.5.2 ; python_version >= "3.9" and python_version < "3.13"
scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13" scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
sentence-transformers[train]==3.0.1 ; python_version >= "3.9" and python_version < "3.13" sentence-transformers[train]==3.0.1 ; 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==73.0.1 ; python_version >= "3.9" and python_version < "3.13" setuptools==75.2.0 ; 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==1.12.1 ; python_version >= "3.9" and python_version < "3.13" sympy==1.12.1 ; python_version >= "3.9" and python_version < "3.13"
threadpoolctl==3.5.0 ; python_version >= "3.9" and python_version < "3.13" threadpoolctl==3.5.0 ; python_version >= "3.9" and python_version < "3.13"
tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13" tokenizers==0.20.1 ; python_version >= "3.9" and python_version < "3.13"
torch==2.4.0a0+git74cd574 ; python_version >= "3.9" and python_version < "3.13"
tqdm==4.66.5 ; python_version >= "3.9" and python_version < "3.13" tqdm==4.66.5 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.43.4 ; python_version >= "3.9" and python_version < "3.13" transformers==4.45.2 ; python_version >= "3.9" and python_version < "3.13"
transformers[sentencepiece]==4.43.4 ; python_version >= "3.9" and python_version < "3.13" transformers[sentencepiece]==4.45.2 ; python_version >= "3.9" and python_version < "3.13"
triton==3.0.0 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version < "3.13" and python_version >= "3.9" triton==3.0.0 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version < "3.13" and python_version >= "3.9"
typer==0.7.0 ; python_version >= "3.9" and python_version < "3.13" typer==0.7.0 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.12.2 ; python_version >= "3.9" and python_version < "3.13" typing-extensions==4.12.2 ; python_version >= "3.9" and python_version < "3.13"
tzdata==2024.1 ; python_version >= "3.9" and python_version < "3.13" tzdata==2024.2 ; python_version >= "3.9" and python_version < "3.13"
urllib3==2.2.2 ; python_version >= "3.9" and python_version < "3.13" urllib3==2.2.3 ; 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==3.5.0 ; python_version >= "3.9" and python_version < "3.13" xxhash==3.5.0 ; python_version >= "3.9" and python_version < "3.13"
yarl==1.9.4 ; python_version >= "3.9" and python_version < "3.13" yarl==1.16.0 ; python_version >= "3.9" and python_version < "3.13"
zipp==3.20.0 ; python_version >= "3.9" and python_version < "3.13" zipp==3.20.2 ; python_version >= "3.9" and python_version < "3.13"