Update base for Update on "[ET-VK][ez][testing] Remove conv2d test in compute_api_test + reduce stdout logging"

## Changes

Some changes to `vulkan_compute_api_test`:

* Remove `conv2d_prepack_test`. D74523774 / #11306 recently changed the conv2d prepack shader to use push constants, and since this test uses the "old" vulkan compute API (which doesn't support push constants) the test broke. Operator tests at this point are handled by `compute_graph_op_tests` anyway so just remove this test.
* Make it so that verbose logging in `test_to_copy` only occurs in `VULKAN_DEBUG` is defined
* Disable `test_etvk_copy_channel_offset_node*` tests, as these tests fail on some platforms (i.e. devGPU, windows, mac) likely due to an error in the implementation of the op.

Differential Revision: [D76156109](https://our.internmc.facebook.com/intern/diff/D76156109/)

[ghstack-poisoned]

Author: SS-JIA

.ci/scripts/build_llama_android.sh

@@ -42,7 +42,6 @@ build_llama_runner() {
     popd
     ANDROID_ABI=arm64-v8a
     cmake -DBUCK2="${BUCK2}" \
-    -DBUILD_TESTING=OFF \
     -DCMAKE_TOOLCHAIN_FILE="$ANDROID_NDK"/build/cmake/android.toolchain.cmake  \
     -DANDROID_ABI="${ANDROID_ABI}" \
     -DCMAKE_INSTALL_PREFIX=cmake-android-out \

.ci/scripts/test_llama.sh

@@ -169,7 +169,6 @@ cmake_build_llama_runner() {
     popd
     dir="examples/models/llama"
     retry cmake \
-        -DBUILD_TESTING=OFF \
         -DCMAKE_INSTALL_PREFIX=cmake-out \
         -DCMAKE_BUILD_TYPE="$CMAKE_BUILD_TYPE" \
         -Bcmake-out/${dir} \

.ci/scripts/test_llama_torchao_lowbit.sh

@@ -40,7 +40,6 @@ cmake --build cmake-out -j16 --target install --config Release
 
 # Install llama runner with torchao
 cmake -DPYTHON_EXECUTABLE=python \
-    -DBUILD_TESTING=OFF \
     -DCMAKE_BUILD_TYPE=Release \
     -DEXECUTORCH_BUILD_KERNELS_CUSTOM=ON \
     -DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON \

.ci/scripts/test_llava.sh

@@ -64,10 +64,9 @@ cmake_install_executorch_libraries_for_android() {
 
 
 LLAVA_COMMON_CMAKE_ARGS="                        \
-        -DBUILD_TESTING=OFF                      \
         -DPYTHON_EXECUTABLE="$PYTHON_EXECUTABLE" \
         -DCMAKE_INSTALL_PREFIX=${BUILD_DIR}      \
-        -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}   \
+        -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}         \
         -DEXECUTORCH_BUILD_KERNELS_CUSTOM=ON     \
         -DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON  \
         -DEXECUTORCH_BUILD_XNNPACK=ON"

examples/demo-apps/apple_ios/LLaMA/LLaMARunner/LLaMARunner/Exported/LLaMARunner.mm

@@ -14,7 +14,6 @@
 
 using executorch::extension::llm::GenerationConfig;
 using executorch::extension::llm::Image;
-using executorch::extension::llm::TextLLMRunner;
 using executorch::runtime::Error;
 
 NSErrorDomain const LLaMARunnerErrorDomain = @"LLaMARunnerErrorDomain";
@@ -24,15 +23,15 @@ @interface LLaMARunner ()<ExecuTorchLogSink>
 @end
 
 @implementation LLaMARunner {
-  std::unique_ptr<TextLLMRunner> _runner;
+  std::unique_ptr<example::Runner> _runner;
 }
 
 - (instancetype)initWithModelPath:(NSString*)modelPath
                     tokenizerPath:(NSString*)tokenizerPath {
   self = [super init];
   if (self) {
     [ExecuTorchLog.sharedLog addSink:self];
-    _runner = example::create_llama_runner(
+    _runner = example::Runner::create(
         modelPath.UTF8String, tokenizerPath.UTF8String);
   }
   return self;

examples/models/llama/CMakeLists.txt

@@ -220,6 +220,7 @@ endif()
 target_include_directories(
   llama_main
   PUBLIC ${_common_include_directories}
+         ${EXECUTORCH_ROOT}/extension/llm/tokenizers/include
 )
 target_link_libraries(llama_main PUBLIC llama_runner ${link_libraries})
 target_compile_options(llama_main PUBLIC ${_common_compile_options})

examples/models/llama/main.cpp

@@ -81,13 +81,8 @@ int32_t main(int32_t argc, char** argv) {
   }
 #endif
   // create llama runner
-  std::unique_ptr<::executorch::extension::llm::TextLLMRunner> runner =
-      example::create_llama_runner(model_path, tokenizer_path, data_path);
-
-  if (runner == nullptr) {
-    ET_LOG(Error, "Failed to create llama runner");
-    return 1;
-  }
+  std::unique_ptr<example::Runner> runner =
+      example::Runner::create(model_path, tokenizer_path, data_path);
 
   if (warmup) {
     runner->warmup(prompt, /*max_new_tokens=*/seq_len);

examples/models/llama/runner/CMakeLists.txt

@@ -52,20 +52,23 @@ else()
   add_library(llama_runner SHARED ${_llama_runner__srcs})
 endif()
 
-# For extension_llm_runner
-if(NOT TARGET extension_llm_runner)
-  add_subdirectory(
-    ${EXECUTORCH_ROOT}/extension/llm/runner
-    ${CMAKE_CURRENT_BINARY_DIR}/../../../../extension/llm/runner
-  )
-endif()
-
 set(llama_runner_deps executorch_core extension_data_loader extension_module
-                      extension_tensor extension_flat_tensor extension_llm_runner
+                      extension_tensor extension_flat_tensor
 )
 
 target_link_libraries(llama_runner PUBLIC ${llama_runner_deps})
 
+target_include_directories(
+  llama_runner
+  INTERFACE ${_common_include_directories}
+)
+
+# Include tokenizers dependency
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+add_subdirectory(
+  ${EXECUTORCH_ROOT}/extension/llm/tokenizers
+  ${CMAKE_CURRENT_BINARY_DIR}/tokenizers
+)
 target_link_libraries(
   llama_runner PUBLIC tokenizers
 )