Deployed caf869d to master with MkDocs 1.6.0 and mike 2.1.1

master/modelserving/v1beta1/triton/huggingface/index.html

@@ -1202,11 +1202,11 @@ <h2 id="deploy-inferenceservice-with-triton-and-hugging-face-runtime">Deploy Inf
 <span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">huggingface-triton</span>
 <span class="nt">spec</span><span class="p">:</span>
 <span class="nt">predictor</span><span class="p">:</span>
-<span class="w">    </span><span class="nt">model</span><span class="p">:</span>
+<span class="w">  </span><span class="nt">model</span><span class="p">:</span>
 <span class="w">    </span><span class="nt">args</span><span class="p">:</span>
 <span class="w">    </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">--log-verbose=1</span>
 <span class="w">    </span><span class="nt">modelFormat</span><span class="p">:</span>
-<span class="w">        </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">triton</span>
+<span class="w">      </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">triton</span>
 <span class="w">    </span><span class="nt">protocolVersion</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v2</span>
 <span class="w">    </span><span class="nt">resources</span><span class="p">:</span>
 <span class="w">      </span><span class="nt">limits</span><span class="p">:</span>
@@ -1219,13 +1219,13 @@ <h2 id="deploy-inferenceservice-with-triton-and-hugging-face-runtime">Deploy Inf
 <span class="w">    </span><span class="nt">runtimeVersion</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">23.10-py3</span>
 <span class="w">    </span><span class="nt">storageUri</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gs://kfserving-examples/models/triton/huggingface/model_repository</span>
 <span class="nt">transformer</span><span class="p">:</span>
-<span class="w">    </span><span class="nt">containers</span><span class="p">:</span>
-<span class="w">    </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">args</span><span class="p">:</span>
+<span class="w">  </span><span class="nt">containers</span><span class="p">:</span>
+<span class="w">  </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">args</span><span class="p">:</span>
 <span class="w">    </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">--model_name=bert</span>
 <span class="w">    </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">--model_id=bert-base-uncased</span>
 <span class="w">    </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">--predictor_protocol=v2</span>
 <span class="w">    </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">--tensor_input_names=input_ids</span>
-<span class="w">    </span><span class="nt">image</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">kserve/huggingfaceserver:v0.12.0</span>
+<span class="w">    </span><span class="nt">image</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">kserve/huggingfaceserver:v0.13.0</span>
 <span class="w">    </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">kserve-container</span>
 <span class="w">    </span><span class="nt">resources</span><span class="p">:</span>
 <span class="w">      </span><span class="nt">limits</span><span class="p">:</span>

master/modelserving/v1beta1/triton/huggingface/triton_runtime.yaml

@@ -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: