mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-04-19 22:48:39 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat(type): provide structured annotations stubs (#663)

Browse Source 
* feat(type): provide client stubs

separation of concern for more brevity code base

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

* docs: update changelog

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
2023-11-16 02:58:45 -05:00
committed by GitHub
parent c6264f3af7
commit 4a6f13ddd2
32 changed files with 795 additions and 582 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
openllm-python/src/openllm_cli/_factory.py
View File

@@ -429,7 +429,7 @@ def workers_per_resource_option(
- ``round_robin``: Similar behaviour when setting ``--workers-per-resource 1``. This is useful for smaller models.
- ``conserved``: This will determine the number of available GPU resources, and only assign one worker for the LLMRunner. For example, if ther are 4 GPUs available, then ``conserved`` is equivalent to ``--workers-per-resource 0.25``.
- ``conserved``: This will determine the number of available GPU resources. For example, if ther are 4 GPUs available, then ``conserved`` is equivalent to ``--workers-per-resource 0.25``.
"""
+ (
"""\n

4
openllm-python/src/openllm_cli/entrypoint.py
View File

@@ -77,6 +77,7 @@ from openllm_core.utils import (
compose,
configure_logging,
first_not_none,
gen_random_uuid,
get_debug_mode,
get_disable_warnings,
get_quiet_mode,
@@ -986,7 +987,6 @@ def build_command(
> To build the bento with compiled OpenLLM, make sure to prepend HATCH_BUILD_HOOKS_ENABLE=1. Make sure that the deployment
> target also use the same Python version and architecture as build machine.
"""
from openllm._llm import normalise_model_name
from openllm.serialisation.transformers.weights import has_safetensors_weights
if model_id in openllm.CONFIG_MAPPING:
@@ -1046,7 +1046,7 @@ def build_command(
labels = dict(llm.identifying_params)
labels.update({'_type': llm.llm_type, '_framework': llm.__llm_backend__})
with fs.open_fs(f'temp://llm_{normalise_model_name(model_id)}') as llm_fs:
with fs.open_fs(f'temp://llm_{gen_random_uuid()}') as llm_fs:
dockerfile_template_path = None
if dockerfile_template:
with dockerfile_template:

11
openllm-python/src/openllm_cli/extension/build_base_container.py
View File

@@ -43,16 +43,13 @@ def build_container(
"This utility can only be run within OpenLLM git repository. Clone it first with 'git clone https://github.com/bentoml/OpenLLM.git'"
)
if not registries:
tags: dict[str | LiteralContainerRegistry, str] = {
alias: f'{value}:{openllm.bundle.get_base_container_tag(version_strategy)}'
for alias, value in openllm.bundle.CONTAINER_NAMES.items()
tags = {
alias: openllm.bundle.RefResolver.construct_base_image(alias, version_strategy)
for alias in openllm.bundle.CONTAINER_NAMES
}
else:
registries = [registries] if isinstance(registries, str) else list(registries)
tags = {
name: f'{openllm.bundle.CONTAINER_NAMES[name]}:{openllm.bundle.get_base_container_tag(version_strategy)}'
for name in registries
}
tags = {name: openllm.bundle.RefResolver.construct_base_image(name, version_strategy) for name in registries}
try:
outputs = _BUILDER.build(
file=pathlib.Path(__file__).parent.joinpath('Dockerfile').resolve().__fspath__(),