Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

add resources to input downloader in the ollama plugin #2754

Merged
merged 4 commits into from
Sep 18, 2024
Merged

add resources to input downloader in the ollama plugin #2754

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
eb78b9a
add resources to input downloader in the ollama plugin
samhita-alla Sep 17, 2024
0f32bc6
remove gpu
samhita-alla Sep 17, 2024
cbea4ab
make cpu configurable
samhita-alla Sep 17, 2024
5426216
set cpu to 2
samhita-alla Sep 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions plugins/flytekit-inference/flytekitplugins/inference/ollama/serve.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,8 @@ def __init__(
cpu: int = 1,
gpu: int = 1,
mem: str = "15Gi",
download_inputs_mem: str = "500Mi",
download_inputs_cpu: int = 2,
):
"""Initialize Ollama class for managing a Kubernetes pod template.

Expand All @@ -40,6 +42,8 @@ def __init__(
:param cpu: The number of CPU cores requested for the container. Default is 1.
:param gpu: The number of GPUs requested for the container. Default is 1.
:param mem: The amount of memory requested for the container, specified as a string. Default is "15Gi".
:param download_inputs_mem: The amount of memory requested for downloading inputs, specified as a string. Default is "500Mi".
:param download_inputs_cpu: The number of CPU cores requested for downloading inputs. Default is 2.
"""
self._model_name = model.name
self._model_mem = model.mem
Expand All @@ -52,6 +56,8 @@ def __init__(
cpu=cpu,
gpu=gpu,
mem=mem,
download_inputs_mem=download_inputs_mem,
download_inputs_cpu=download_inputs_cpu,
download_inputs=(True if self._model_modelfile and "{inputs" in self._model_modelfile else False),
)

Expand Down
14 changes: 14 additions & 0 deletions plugins/flytekit-inference/flytekitplugins/inference/sidecar_template.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,8 @@ def __init__(
mem: str = "1Gi",
env: Optional[dict[str, str]] = None,
download_inputs: bool = False,
download_inputs_mem: str = "500Mi",
download_inputs_cpu: int = 2,
):
from kubernetes.client.models import (
V1Container,
Expand All @@ -34,6 +36,8 @@ def __init__(
self._cpu = cpu
self._gpu = gpu
self._mem = mem
self._download_inputs_mem = download_inputs_mem
self._download_inputs_cpu = download_inputs_cpu
self._env = env
self._download_inputs = download_inputs

Expand Down Expand Up @@ -138,6 +142,16 @@ def __init__(
V1VolumeMount(name="shared-data", mount_path="/shared"),
V1VolumeMount(name="tmp", mount_path="/tmp"),
],
resources=V1ResourceRequirements(
requests={
"cpu": self._download_inputs_cpu,
"memory": self._download_inputs_mem,
},
limits={
"cpu": self._download_inputs_cpu,
"memory": self._download_inputs_mem,
},
),
),
)

Expand Down
Loading