Hugging Face's logo

embedl
/
all-MiniLM-L6-v2-quantized-trt

Sentence Similarity
TensorRT
ONNX
quantization
edge
embedl
Model card Files
xet
 Community
dann-od commited on
Commit
1e81cb5
·
verified ·
1 Parent(s): 9a4327b

Added a memory usage plot

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -108,7 +108,9 @@ Latency measured with TensorRT + `trtexec`, GPU compute time only
108
  (`--noDataTransfers`), CUDA Graph + Spin Wait enabled, clocks locked
109
  (`nvpmodel -m 0 && jetson_clocks` on Jetson).
110
 
111
- <img src="https://huggingface.co/datasets/embedl/documentation-images/resolve/main/all-MiniLM-L6-v2-quantized-trt/all-MiniLM-L6-v2-quantized-trt__orin-mountain-view.svg" alt="All Minilm L6 V2 benchmark on NVIDIA Jetson AGX Orin">
 
 
112
 
113
  ### NVIDIA Jetson AGX Orin
114
 
 
108
  (`--noDataTransfers`), CUDA Graph + Spin Wait enabled, clocks locked
109
  (`nvpmodel -m 0 && jetson_clocks` on Jetson).
110
 
111
+ <img src="https://huggingface.co/datasets/embedl/documentation-images/resolve/main/all-MiniLM-L6-v2-quantized-trt/all-MiniLM-L6-v2-quantized-trt__orin-mountain-view__latency.svg" alt="All Minilm L6 V2 latency on NVIDIA Jetson AGX Orin">
112
+
113
+ <img src="https://huggingface.co/datasets/embedl/documentation-images/resolve/main/all-MiniLM-L6-v2-quantized-trt/all-MiniLM-L6-v2-quantized-trt__orin-mountain-view__memory.svg" alt="All Minilm L6 V2 peak memory on NVIDIA Jetson AGX Orin">
114
 
115
  ### NVIDIA Jetson AGX Orin
116