huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-26 12:32:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Upgrade to SynapseAI 1.19 (#259)

Browse Source 
Signed-off-by: yuanwu <yuan.wu@intel.com>
This commit is contained in:
Yuan Wu 2024-12-27 00:33:24 +08:00 committed by GitHub
parent 5291f652a1
commit 46b556805b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Dockerfile
View File

@ -41,7 +41,7 @@ COPY launcher launcher
RUN cargo build --profile release-opt RUN cargo build --profile release-opt
# Text Generation Inference base image # Text Generation Inference base image
FROM vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest as base FROM vault.habana.ai/gaudi-docker/1.19.0/ubuntu22.04/habanalabs/pytorch-installer-2.5.1:latest AS base
ENV ATTENTION=default ENV ATTENTION=default
ENV PREFIX_CACHING=0 ENV PREFIX_CACHING=0
@ -75,7 +75,7 @@ RUN cd server && \
make gen-server && \ make gen-server && \
pip install --no-deps -r requirements.txt && \ pip install --no-deps -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@1.18.0 && \ pip install git+https://github.com/HabanaAI/DeepSpeed.git@1.19.0 && \
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

2
server/pyproject.toml
View File

@ -22,7 +22,7 @@ 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 = "1.14.1" optimum-habana = "1.15.0"
transformers = "4.45.2" transformers = "4.45.2"
numpy = "1.26.4" numpy = "1.26.4"
accelerate = "0.33.0" accelerate = "0.33.0"

6
server/requirements.txt
View File

@ -12,7 +12,7 @@ colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_p
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==3.0.1 ; 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==0.31.0 ; python_version >= "3.9" and python_version < "3.13"
dill==0.3.7 ; python_version >= "3.9" and python_version < "3.13" dill==0.3.7 ; python_version >= "3.9" and python_version < "3.13"
filelock==3.16.1 ; 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"
@ -46,7 +46,7 @@ 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==1.14.1 ; python_version >= "3.9" and python_version < "3.13" optimum-habana==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
optimum==1.23.2 ; 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==2.2.3 ; python_version >= "3.9" and python_version < "3.13" pandas==2.2.3 ; python_version >= "3.9" and python_version < "3.13"
@ -67,7 +67,7 @@ requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13"
safetensors==0.4.5 ; python_version >= "3.9" and python_version < "3.13" safetensors==0.4.5 ; python_version >= "3.9" and python_version < "3.13"
scikit-learn==1.5.2 ; 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]==3.2.1 ; 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==75.2.0 ; 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"

7
server/text_generation_server/models/causal_lm.py
View File

@ -717,11 +717,12 @@ class CausalLM(Model):
} }
if model.config.model_type in ["llama", "mistral", "starcoder2", "qwen2", "falcon"]: if model.config.model_type in ["llama", "mistral", "starcoder2", "qwen2", "falcon", "gpt_bigcode"]:
if model.config.model_type not in ["falcon"]: if model.config.model_type not in ["falcon", "gpt_bigcode"]:
self.kwargs["attn_softmax_bf16"] = True self.kwargs["attn_softmax_bf16"] = True
self.kwargs["trim_logits"] = True if model.config.model_type not in ["gpt_bigcode"]:
self.kwargs["trim_logits"] = True
if os.getenv("USE_FLASH_ATTENTION", "false").lower() == "true": if os.getenv("USE_FLASH_ATTENTION", "false").lower() == "true":
self.kwargs["use_flash_attention"] = True self.kwargs["use_flash_attention"] = True

0
server/text_generation_server/pb/.gitignore vendored Normal file → Executable file
View File