mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-02-19 15:18:12 -05:00
Code Issues Packages Projects Releases Wiki Activity

refactor: focus (#730)

Browse Source 
* perf: remove based images

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: update changelog

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: move dockerifle to run on release only

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: cleanup unused types

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
Aaron Pham
2023-11-24 01:11:31 -05:00
committed by GitHub
parent 52a44b1bfa
commit aab173cd99
19 changed files with 168 additions and 679 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
openllm-python/src/openllm/__init__.py
View File

@@ -1,30 +1,17 @@
import logging as _logging
import os as _os
import pathlib as _pathlib
import warnings as _warnings
import logging as _logging, os as _os, pathlib as _pathlib, warnings as _warnings
from openllm_cli import _sdk
from . import utils as utils
if utils.DEBUG:
utils.set_debug_mode(True)
_logging.basicConfig(level=_logging.NOTSET)
utils.set_debug_mode(True); _logging.basicConfig(level=_logging.NOTSET)
else:
# configuration for bitsandbytes before import
_os.environ['BITSANDBYTES_NOWELCOME'] = _os.environ.get('BITSANDBYTES_NOWELCOME', '1')
# NOTE: The following warnings from bitsandbytes, and probably not that important for users to see when DEBUG is False
_warnings.filterwarnings(
'ignore', message='MatMul8bitLt: inputs will be cast from torch.float32 to float16 during quantization'
)
_warnings.filterwarnings(
'ignore', message='MatMul8bitLt: inputs will be cast from torch.bfloat16 to float16 during quantization'
)
_warnings.filterwarnings('ignore', message='MatMul8bitLt: inputs will be cast from torch.float32 to float16 during quantization')
_warnings.filterwarnings('ignore', message='MatMul8bitLt: inputs will be cast from torch.bfloat16 to float16 during quantization')
_warnings.filterwarnings('ignore', message='The installed version of bitsandbytes was compiled without GPU support.')
# NOTE: ignore the following warning from ghapi as it is not important for users
_warnings.filterwarnings(
'ignore', message='Neither GITHUB_TOKEN nor GITHUB_JWT_TOKEN found: running as unauthenticated'
)
_warnings.filterwarnings('ignore', message='Neither GITHUB_TOKEN nor GITHUB_JWT_TOKEN found: running as unauthenticated')
COMPILED = _pathlib.Path(__file__).suffix in ('.pyd', '.so')