Merge branch 'main' into angelayi/aoti_api_update

Author: Jack-Khuu

torchchat/generate.py

@@ -1192,6 +1192,8 @@ def callback(x, *, done_generating=False):
                     max_seq_length=max_seq_length,
                     attention_backend=self.builder_args.attention_backend,
                 )
+                if generator_args.chat_mode:
+                    start_pos += encoded.size(0)
                 for token_tensor, metrics in generator_func:
                     if token_tensor is not None:
                         start_pos += token_tensor.size(0)

torchchat/utils/scripts/install_utils.sh

@@ -88,7 +88,7 @@ install_executorch_python_libs() {
   echo "Building and installing python libraries"
   if [ "${ENABLE_ET_PYBIND}" = false ]; then
       echo "Not installing pybind"
-      bash ./install_requirements.sh
+      bash ./install_requirements.sh --pybind off
   else
       echo "Installing pybind"
       bash ./install_requirements.sh --pybind xnnpack