mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-20 18:45:00 +00:00
feat: create bash library to handle install/run/test of python backends (#2286)
* feat: create bash library to handle install/run/test of python backends Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * chore: minor cleanup Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove incorrect LIMIT_TARGETS from parler-tts Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: update runUnitests to handle running tests from a custom test file Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * chore: document runUnittests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
This commit is contained in:
cryptk
GitHub
parent
7f4febd6c2
commit
e2de8a88f7
106 changed files with 425 additions and 1606 deletions
|
|
@ -22,4 +22,4 @@ backend_pb2_grpc.py backend_pb2.py:
|
|||
|
||||
.PHONY: clean
|
||||
clean: protogen-clean
|
||||
$(RM) -r venv source
|
||||
$(RM) -r venv source __pycache__
|
||||
|
|
@ -14,9 +14,9 @@ import torch
|
|||
import torch.nn.functional as F
|
||||
from torch import version as torch_version
|
||||
|
||||
from tokenizer import ExLlamaTokenizer
|
||||
from generator import ExLlamaGenerator
|
||||
from model import ExLlama, ExLlamaCache, ExLlamaConfig
|
||||
from source.tokenizer import ExLlamaTokenizer
|
||||
from source.generator import ExLlamaGenerator
|
||||
from source.model import ExLlama, ExLlamaCache, ExLlamaConfig
|
||||
|
||||
_ONE_DAY_IN_SECONDS = 60 * 60 * 24
|
||||
|
||||
|
|
@ -1,56 +0,0 @@
|
|||
name: exllama
|
||||
channels:
|
||||
- defaults
|
||||
dependencies:
|
||||
- _libgcc_mutex=0.1=main
|
||||
- _openmp_mutex=5.1=1_gnu
|
||||
- bzip2=1.0.8=h7b6447c_0
|
||||
- ca-certificates=2023.08.22=h06a4308_0
|
||||
- ld_impl_linux-64=2.38=h1181459_1
|
||||
- libffi=3.4.4=h6a678d5_0
|
||||
- libgcc-ng=11.2.0=h1234567_1
|
||||
- libgomp=11.2.0=h1234567_1
|
||||
- libstdcxx-ng=11.2.0=h1234567_1
|
||||
- libuuid=1.41.5=h5eee18b_0
|
||||
- ncurses=6.4=h6a678d5_0
|
||||
- openssl=3.0.11=h7f8727e_2
|
||||
- pip=23.2.1=py311h06a4308_0
|
||||
- python=3.11.5=h955ad1f_0
|
||||
- readline=8.2=h5eee18b_0
|
||||
- setuptools=68.0.0=py311h06a4308_0
|
||||
- sqlite=3.41.2=h5eee18b_0
|
||||
- tk=8.6.12=h1ccaba5_0
|
||||
- tzdata=2023c=h04d1e81_0
|
||||
- wheel=0.41.2=py311h06a4308_0
|
||||
- xz=5.4.2=h5eee18b_0
|
||||
- zlib=1.2.13=h5eee18b_0
|
||||
- pip:
|
||||
- filelock==3.12.4
|
||||
- fsspec==2023.9.2
|
||||
- grpcio==1.63.0
|
||||
- jinja2==3.1.2
|
||||
- markupsafe==2.1.3
|
||||
- mpmath==1.3.0
|
||||
- networkx==3.1
|
||||
- ninja==1.11.1
|
||||
- protobuf==4.24.4
|
||||
- nvidia-cublas-cu12==12.1.3.1
|
||||
- nvidia-cuda-cupti-cu12==12.1.105
|
||||
- nvidia-cuda-nvrtc-cu12==12.1.105
|
||||
- nvidia-cuda-runtime-cu12==12.1.105
|
||||
- nvidia-cudnn-cu12==8.9.2.26
|
||||
- nvidia-cufft-cu12==11.0.2.54
|
||||
- nvidia-curand-cu12==10.3.2.106
|
||||
- nvidia-cusolver-cu12==11.4.5.107
|
||||
- nvidia-cusparse-cu12==12.1.0.106
|
||||
- nvidia-nccl-cu12==2.18.1
|
||||
- nvidia-nvjitlink-cu12==12.2.140
|
||||
- nvidia-nvtx-cu12==12.1.105
|
||||
- safetensors==0.3.2
|
||||
- sentencepiece==0.1.99
|
||||
- sympy==1.12
|
||||
- torch==2.1.0
|
||||
- triton==2.1.0
|
||||
- typing-extensions==4.8.0
|
||||
- numpy
|
||||
prefix: /opt/conda/envs/exllama
|
||||
|
|
@ -1,37 +1,13 @@
|
|||
#!/bin/bash
|
||||
set -ex
|
||||
set -e
|
||||
|
||||
BUILD_ISOLATION_FLAG=""
|
||||
LIMIT_TARGETS="cublas"
|
||||
|
||||
if [ "$BUILD_TYPE" != "cublas" ]; then
|
||||
echo "[exllama] Attention!!! Nvidia GPU is required - skipping installation"
|
||||
exit 0
|
||||
fi
|
||||
source $(dirname $0)/../common/libbackend.sh
|
||||
|
||||
MY_DIR="$(dirname -- "${BASH_SOURCE[0]}")"
|
||||
|
||||
uv venv ${MY_DIR}/venv
|
||||
source ${MY_DIR}/venv/bin/activate
|
||||
|
||||
if [ -f "requirements-install.txt" ]; then
|
||||
# If we have a requirements-install.txt, it means that a package does not properly declare it's build time
|
||||
# dependencies per PEP-517, so we have to set up the proper build environment ourselves, and then install
|
||||
# the package without build isolation
|
||||
BUILD_ISOLATION_FLAG="--no-build-isolation"
|
||||
uv pip install --requirement ${MY_DIR}/requirements-install.txt
|
||||
fi
|
||||
|
||||
uv pip install ${BUILD_ISOLATION_FLAG} --requirement ${MY_DIR}/requirements.txt
|
||||
|
||||
if [ -f "requirements-${BUILD_TYPE}.txt" ]; then
|
||||
uv pip install ${BUILD_ISOLATION_FLAG} --requirement ${MY_DIR}/requirements-${BUILD_TYPE}.txt
|
||||
fi
|
||||
installRequirements
|
||||
|
||||
git clone https://github.com/turboderp/exllama $MY_DIR/source
|
||||
uv pip install ${BUILD_ISOLATION_FLAG} --requirement ${MY_DIR}/source/requirements.txt
|
||||
|
||||
cp -rfv ./*py $MY_DIR/source/
|
||||
|
||||
if [ "$PIP_CACHE_PURGE" = true ] ; then
|
||||
pip cache purge
|
||||
fi
|
||||
cp -v ./*py $MY_DIR/source/
|
||||
|
|
|
|||
|
|
@ -1,10 +1,7 @@
|
|||
#!/bin/bash
|
||||
LIMIT_TARGETS="cublas"
|
||||
BACKEND_FILE="${MY_DIR}/source/backend.py"
|
||||
|
||||
##
|
||||
## A bash script wrapper that runs the exllama server with uv
|
||||
source $(dirname $0)/../common/libbackend.sh
|
||||
|
||||
MY_DIR="$(dirname -- "${BASH_SOURCE[0]}")"
|
||||
|
||||
source $MY_DIR/venv/bin/activate
|
||||
|
||||
python $MY_DIR/source/exllama.py $@
|
||||
startBackend $@
|
||||
|
|
@ -1,16 +1,6 @@
|
|||
#!/bin/bash
|
||||
##
|
||||
## A bash script wrapper that runs python unittests
|
||||
set -e
|
||||
|
||||
MY_DIR="$(dirname -- "${BASH_SOURCE[0]}")"
|
||||
source $(dirname $0)/../common/libbackend.sh
|
||||
|
||||
source $MY_DIR/venv/bin/activate
|
||||
|
||||
if [ -f "${MY_DIR}/test.py" ]; then
|
||||
pushd ${MY_DIR}
|
||||
python -m unittest test.py
|
||||
popd
|
||||
else
|
||||
echo "ERROR: No tests defined for backend!"
|
||||
exit 1
|
||||
fi
|
||||
runUnittests
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue