Merge branch 'main' into multimodal_cli_pipeline

Author: vmpuri

.gitignore

@@ -6,6 +6,7 @@ __pycache__/
 # C extensions
 *.so
 
+.vscode
 .model-artifacts/
 .venv
 .torchchat
@@ -15,6 +16,7 @@ build/android/*
 et-build/*
 runner-et/cmake-out/*
 runner-aoti/cmake-out/*
+cmake-out/
 
 # pte files
 *.pte
@@ -24,3 +26,7 @@ system_info.txt
 
 # intermediate system file
 .DS_Store
+
+# build artifacts
+checkpoints/
+exportedModels/

torchchat/edge/docs/Android.md

@@ -37,10 +37,10 @@ In your app working directory (for example executorch/examples/demo-apps/android
 copy the AAR to your app libs:
 ```bash
 mkdir -p app/libs
-cp ${TORCHCHAT_ROOT}/android/torchchat/app/libs/executorch.aar ${YOUR_APP_ROOT}/app/libs/executorch.jar
+cp ${TORCHCHAT_ROOT}/android/torchchat/app/libs/executorch.aar ${YOUR_APP_ROOT}/app/libs/executorch.aar
 ```
 
-In your Java app, add the jar file path to your gradle build rule.
+In your Java app, add the aar file path to your gradle build rule.
 ```
 # app/build.grardle.kts
 dependencies {

torchchat/generate.py

@@ -841,7 +841,7 @@ def chat(
         )
         for i in range(num_samples):
             device_sync(device=self.builder_args.device)
-            if i >= 0 and generator_args.chat_mode:
+            if generator_args.chat_mode:
                 prompt = input("User: ")
                 if prompt == "/bye":
                     print("Exiting Chat.\n")
@@ -884,7 +884,6 @@ def chat(
                     )
                     break
 
-            if generator_args.chat_mode and i >= 0:
                 print("Model: ", end="")
 
                 buffer = []