mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-02-07 22:33:28 -05:00
Code Issues Packages Projects Releases Wiki Activity

chore: move out the template to separate files

Browse Source 
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
Aaron Pham
2024-04-02 03:24:11 +00:00
parent fbab26ddc4
commit 4661838964
2 changed files with 7 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
openllm-python/src/_openllm_tiny/Dockerfile.j2 Normal file
View File

@@ -0,0 +1,4 @@
{% extends bento_base_template %}
{% block SETUP_BENTO_BASE_IMAGE %}
{{ super() }}
{% endblock %}

12
openllm-python/src/_openllm_tiny/_entrypoint.py
View File

@@ -51,12 +51,6 @@ max_model_len=orjson.loads(coreutils.getenv('max_model_len', default=orjson.dump
gpu_memory_utilization=orjson.loads(coreutils.getenv('gpu_memory_utilization', default=orjson.dumps({__gpu_memory_utilization__}), var=['GPU_MEMORY_UTILISATION']))
services_config=orjson.loads(coreutils.getenv('services_config',"""{__services_config__}"""))
'''
_DOCKERFILE_TEMPLATE = """\
{% extends bento_base_template %}
{% block SETUP_BENTO_BASE_IMAGE %}
{{ super() }}
{% endblock %}
"""
class ItemState(enum.Enum):
@@ -235,6 +229,7 @@ def start_command(
"""
import transformers
from _bentoml_impl.server import serve_http
from bentoml._internal.service.loader import load
from bentoml._internal.log import configure_server_logging
@@ -284,9 +279,8 @@ def start_command(
working_dir = os.path.abspath(os.path.dirname(__file__))
if sys.path[0] != working_dir:
sys.path.insert(0, working_dir)
load('.', working_dir=working_dir).serve_http(
working_dir=working_dir, reload=check_bool_env('RELOAD', default=False), development_mode=DEBUG
)
load('.', working_dir=working_dir).inject_config()
serve_http('.', working_dir=working_dir, reload=check_bool_env('RELOAD', default=False), development_mode=DEBUG)
def construct_python_options(llm_config, llm_fs):