mirror of
https://github.com/bentoml/OpenLLM.git
synced 2026-02-07 22:33:28 -05:00
fix(base-image): update base image to include cuda for now (#720)
* fix(base-image): update base image to include cuda for now Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com> * fix: build core and client on release images Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com> * chore: cleanup style changes 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:
@@ -71,7 +71,7 @@ def build_container(
|
||||
@click.command(
|
||||
'build_base_container',
|
||||
context_settings=termui.CONTEXT_SETTINGS,
|
||||
help="""Base image builder for BentoLLM.
|
||||
help='''Base image builder for BentoLLM.
|
||||
|
||||
By default, the base image will include custom kernels (PagedAttention via vllm, FlashAttention-v2, etc.) built with CUDA 11.8, Python 3.9 on Ubuntu22.04.
|
||||
Optionally, this can also be pushed directly to remote registry. Currently support ``docker.io``, ``ghcr.io`` and ``quay.io``.
|
||||
@@ -81,7 +81,7 @@ def build_container(
|
||||
This command is only useful for debugging and for building custom base image for extending BentoML with custom base images and custom kernels.
|
||||
|
||||
Note that we already release images on our CI to ECR and GHCR, so you don't need to build it yourself.
|
||||
""",
|
||||
''',
|
||||
)
|
||||
@container_registry_option
|
||||
@click.option(
|
||||
|
||||
@@ -24,7 +24,7 @@ if t.TYPE_CHECKING:
|
||||
def cli(
|
||||
ctx: click.Context, bento: str, machine: bool, _bento_store: BentoStore = Provide[BentoMLContainer.bento_store]
|
||||
) -> str | None:
|
||||
"""Dive into a BentoLLM. This is synonymous to cd $(b get <bento>:<tag> -o path)."""
|
||||
'''Dive into a BentoLLM. This is synonymous to cd $(b get <bento>:<tag> -o path).'''
|
||||
try:
|
||||
bentomodel = _bento_store.get(bento)
|
||||
except bentoml.exceptions.NotFound:
|
||||
|
||||
@@ -13,7 +13,7 @@ from openllm_cli import termui
|
||||
@click.command('list_bentos', context_settings=termui.CONTEXT_SETTINGS)
|
||||
@click.pass_context
|
||||
def cli(ctx: click.Context) -> None:
|
||||
"""List available bentos built by OpenLLM."""
|
||||
'''List available bentos built by OpenLLM.'''
|
||||
mapping = {
|
||||
k: [
|
||||
{
|
||||
|
||||
@@ -18,7 +18,7 @@ if t.TYPE_CHECKING:
|
||||
@click.command('list_models', context_settings=termui.CONTEXT_SETTINGS)
|
||||
@model_name_argument(required=False, shell_complete=model_complete_envvar)
|
||||
def cli(model_name: str | None) -> DictStrAny:
|
||||
"""This is equivalent to openllm models --show-available less the nice table."""
|
||||
'''This is equivalent to openllm models --show-available less the nice table.'''
|
||||
models = tuple(inflection.dasherize(key) for key in openllm.CONFIG_MAPPING.keys())
|
||||
ids_in_local_store = {
|
||||
k: [
|
||||
|
||||
Reference in New Issue
Block a user