Skip to content

Commit

Permalink
Update huggingface triton yaml
Browse files Browse the repository at this point in the history
Signed-off-by: Dan Sun <dsun20@bloomberg.net>
  • Loading branch information
yuzisun committed May 20, 2024
1 parent 41d578f commit caf869d
Show file tree
Hide file tree
Showing 2 changed files with 6 additions and 6 deletions.
10 changes: 5 additions & 5 deletions docs/modelserving/v1beta1/triton/huggingface/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -21,11 +21,11 @@ Create an InferenceService with triton predictor by specifying the `storageUri`
name: huggingface-triton
spec:
predictor:
model:
model:
args:
- --log-verbose=1
modelFormat:
name: triton
name: triton
protocolVersion: v2
resources:
limits:
Expand All @@ -38,13 +38,13 @@ Create an InferenceService with triton predictor by specifying the `storageUri`
runtimeVersion: 23.10-py3
storageUri: gs://kfserving-examples/models/triton/huggingface/model_repository
transformer:
containers:
- args:
containers:
- args:
- --model_name=bert
- --model_id=bert-base-uncased
- --predictor_protocol=v2
- --tensor_input_names=input_ids
image: kserve/huggingfaceserver:v0.12.0
image: kserve/huggingfaceserver:v0.13.0
name: kserve-container
resources:
limits:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ spec:
- --model_id=bert-base-uncased
- --predictor_protocol=v2
- --tensor_input_names=input_ids
image: kserve/huggingfaceserver:latest
image: kserve/huggingfaceserver:v0.13.0
name: kserve-container
resources:
limits:
Expand Down

0 comments on commit caf869d

Please sign in to comment.