
@@ -257,8 +266,8 @@
-
“We're big fans of ONNX Runtime at Writer. ONNX Runtime allows us to run inference on CPUs for models that we would otherwise have to use GPUs for, and allows us to run models on GPUs that would otherwise be too slow to meet our SLAs. The end result is that we can deliver better quality outputs to our users, and at lower costs.”
-
–Sam Havens, Director of NLP Engineering, Writer
+
“ONNX Runtime has been very helpful to us at Writer in optimizing models for production. It lets us deploy more powerful models and still deliver results to our customers with the latency they expect.”
+
–Dave Buchanan, Director of AI and NLP, Writer
diff --git a/images/logos/pieces-logo.png b/images/logos/pieces-logo.png
new file mode 100644
index 0000000000..f1cae4c514
Binary files /dev/null and b/images/logos/pieces-logo.png differ
diff --git a/index.html b/index.html
index 852712aa5d..d54d498641 100644
--- a/index.html
+++ b/index.html
@@ -671,15 +671,22 @@
-

+
+