Change model to fp32

Makefile

@@ -19,8 +19,7 @@ trt:
 		"trtexec --onnx=onnx/model.onnx --saveEngine=$(MODEL_PATH)/model.plan \
 			--minShapes=input:1x3x560x560 \
 			--optShapes=input:2x3x560x560 \
-			--maxShapes=input:8x3x560x560 \
-			--fp16"
+			--maxShapes=input:8x3x560x560"
 
 
 triton:
@@ -32,5 +31,5 @@ triton:
 		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:3,560,560
+	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 0.0.0.0:6001 --concurrency-range 16:16 --shape input:3,560,560
 

model_repository/dinov2_vitl14/1/model.plan

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8d32cc4f1324b661d1770102ba25e826e5a40f6bad9692f2e1ca5b00f417693
-size 46068060
+oid sha256:562a3f73d2826bf6cf828e9a83f8775d11981f9fa65c1489311708fae6cfb6a2
+size 90532324