mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
Andrews ArokiamandGitHub
007fc8dfe4
* initial commit for hugging face model download and load Signed-off-by: Andrews Arokiam <[email protected]> * bug fix on storage initializer Signed-off-by: Andrews Arokiam <[email protected]> * added hf_token and unittests Signed-off-by: Andrews Arokiam <[email protected]> * separate hf-storage-initializer image to reduce image size Signed-off-by: Andrews Arokiam <[email protected]> * review comment changes Signed-off-by: Andrews Arokiam <[email protected]> * snapshot download Signed-off-by: Andrews Arokiam <[email protected]> * use existing image for storage initializer Signed-off-by: Andrews Arokiam <[email protected]> * resolved merge conflicts Signed-off-by: Andrews Arokiam <[email protected]> * added hf storage uri validation Signed-off-by: Andrews Arokiam <[email protected]> * resolved merge conflicts Signed-off-by: Andrews Arokiam <[email protected]> --------- Signed-off-by: Andrews Arokiam <[email protected]>
24 lines
559 B
YAML
24 lines
559 B
YAML
apiVersion: serving.kserve.io/v1beta1
|
|
kind: InferenceService
|
|
metadata:
|
|
name: huggingface-llama2
|
|
spec:
|
|
predictor:
|
|
serviceAccountName: hfserviceacc
|
|
model:
|
|
modelFormat:
|
|
name: huggingface
|
|
args:
|
|
- --model_name=llama2
|
|
- --model_dir=/mnt/models
|
|
- --backend=huggingface
|
|
storageUri: hf://meta-llama/Llama-2-7b-chat-hf
|
|
resources:
|
|
limits:
|
|
cpu: "6"
|
|
memory: 24Gi
|
|
nvidia.com/gpu: "1"
|
|
requests:
|
|
cpu: "6"
|
|
memory: 24Gi
|
|
nvidia.com/gpu: "1" |