Upload model

Makefile

@@ -0,0 +1,10 @@
+triton:
+	docker run --rm -d \
+		--name dinov2_vitl14_triton \
+		-p 8000:8000 --gpus "device=0" -p 8001:8001 -p 8002:8002 \
+		-v $(PWD)/model_repository:/models \
+		nvcr.io/nvidia/tritonserver:23.04-py3 \
+		tritonserver --model-repository=/models
+
+perf:
+	docker run --gpus all --rm -it --net host nvcr.io/nvidia/tritonserver:23.04-py3-sdk perf_analyzer -m dinov2_vitl14 --percentile=95 -i grpc -u 0.0.0.0:8001 --concurrency-range 16:16 --shape input:3,280,280

model_repository/dinov2_vitl14/config.pbtxt

@@ -0,0 +1,24 @@
+name: "dinov2_vitl14"
+max_batch_size: 8
+dynamic_batching {}
+platform: "onnxruntime_onnx"
+instance_group [
+  {
+    count: 1
+    kind: KIND_GPU
+  }
+]
+input [
+  {
+    name: "input"
+    data_type: TYPE_FP32
+    dims: [ 3, 280, 280 ]
+  }
+]
+output [
+  {
+    name: "output"
+    data_type: TYPE_FP32
+    dims: [-1]
+  }
+]

model_repository/dinov2_vitl14/dinov2_vitl14.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c997a103722ead6ba8993152e7d1a1670a2662ad552a43a6649c67660bf2efc
+size 88358024