llava cmakelists (#10127)

See issue: #10096

Copy llama Cmakelists.txt to link custom ops into the binary:


https://github.com/pytorch/executorch/blob/409447d75a1524c1acc8f8ea894c2e13dd723a79/examples/models/llama/CMakeLists.txt#L114


Test plan:

Build:
```
 cmake                                         
-DPYTHON_EXECUTABLE=python         
-DCMAKE_INSTALL_PREFIX=${BUILD_DIR}             
-DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}                 
-DEXECUTORCH_BUILD_KERNELS_CUSTOM=ON             
-DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON          
-DEXECUTORCH_BUILD_XNNPACK=ON         
-DCMAKE_PREFIX_PATH="/home/lfq/.conda/envs/executorch/lib/python3.10/site-packages"         
-Bcmake-out/examples/models/llava                   
examples/models/llava 

cmake --build cmake-out/examples/models/llava/ -j8 --config Debug
```
Run:
```
cmake-out/examples/models/llava/llava_main --model_path=llava.pte --tokenizer_path=tokenizer.bin --image_path=image.pt --prompt="ASSISTANT:" --temperature=0 --seq_len=650

age.pt --prompt="ASSISTANT:" --temperature=0 --seq_len=650
I 00:00:00.001282 executorch:cpuinfo_utils.cpp:62] Reading file /sys/devices/soc0/image_version
I 00:00:00.001330 executorch:cpuinfo_utils.cpp:78] Failed to open midr file /sys/devices/soc0/image_version
I 00:00:00.001353 executorch:cpuinfo_utils.cpp:91] Reading file /sys/devices/system/cpu/cpu0/regs/identification/midr_el1
I 00:00:00.001380 executorch:cpuinfo_utils.cpp:100] Failed to open midr file /sys/devices/system/cpu/cpu0/regs/identification/midr_el1
I 00:00:00.001390 executorch:cpuinfo_utils.cpp:116] CPU info and manual query on # of cpus dont match.
I 00:00:00.001397 executorch:main.cpp:77] Resetting threadpool with num threads = 0
I 00:00:00.001412 executorch:multimodal_runner.h:45] Creating Multimodal LLM runner: model_path=llava.pte, tokenizer_path=tokenizer.bin
I 00:00:00.025122 executorch:main.cpp:107] image size(0): 3, size(1): 240, size(2): 336
I 00:00:21.793359 executorch:llava_runner.cpp:142] RSS after loading model: 6123.457031 MiB (0 if unsupported)
I 00:00:23.059576 executorch:text_prefiller.cpp:95] Prefill token result numel(): 32064
I 00:00:33.459186 executorch:llava_runner.cpp:166] RSS after prompt and image prefill: 6255.707031 MiB (0 if unsupported)
ASSISTANT:I 00:00:33.948606 executorch:text_prefiller.cpp:95] Prefill token result numel(): 32064
 image captures a basketball game in progress, with several players on the court. One player is in the middle of a dunk, while another player is attempting toPyTorchObserver {"prompt_tokens":616,"generated_tokens":33,"model_load_start_ms":1744415212709,"model_load_end_ms":1744415234476,"inference_start_ms":1744415234477,"inference_end_ms":1744415259787,"prompt_eval_end_ms":1744415246632,"first_token_ms":1744415246632,"aggregate_sampling_time_ms":2883588,"SCALING_FACTOR_UNITS_PER_SECOND":1000}
I 00:00:47.103512 executorch:stats.h:104]       Prompt Tokens: 616    Generated Tokens: 33
I 00:00:47.103520 executorch:stats.h:110]       Model Load Time:                21.767000 (seconds)
I 00:00:47.103528 executorch:stats.h:117]       Total inference time:           25.310000 (seconds)              Rate:  1.303832 (tokens/second)
I 00:00:47.103533 executorch:stats.h:127]               Prompt evaluation:      12.155000 (seconds)              Rate:  50.678733 (tokens/second)
I 00:00:47.103538 executorch:stats.h:136]               Generated 33 tokens:    13.155000 (seconds)              Rate:  2.508552 (tokens/second)
I 00:00:47.103542 executorch:stats.h:147]       Time to first generated token:  12.155000 (seconds)
I 00:00:47.103545 executorch:stats.h:153]       Sampling time over 649 tokens:  2883.588000 (seconds)
I 00:00:47.103549 executorch:llava_runner.cpp:178] RSS after finishing text generation: 6255.707031 MiB (0 if unsupported)
```

Author: lucylq

.ci/scripts/test_llava.sh

@@ -154,7 +154,7 @@ run_and_verify() {
         EXPECTED_PREFIX="ASSISTANT: image captures a basketball game in progress, with several players on the court. One of the players is dribbling the ball, while the others are in various"
     else
         # set the expected prefix to be the same as prompt because there's a bug in sdpa_with_kv_cache that causes <unk> tokens.
-        EXPECTED_PREFIX="ASSISTANT:"
+        EXPECTED_PREFIX="ASSISTANT: image"
     fi
     if [[ "${RESULT}" == *"${EXPECTED_PREFIX}"* ]]; then
         echo "Expected result prefix: ${EXPECTED_PREFIX}"

examples/models/llava/CMakeLists.txt

@@ -15,7 +15,7 @@
 # ~~~
 # It should also be cmake-lint clean.
 #
-cmake_minimum_required(VERSION 3.19)
+cmake_minimum_required(VERSION 3.24)  # 3.24 is required for WHOLE_ARCHIVE
 project(llava)
 
 # Duplicating options as root CMakeLists.txt
@@ -124,7 +124,7 @@ target_link_options_shared_lib(quantized_ops_lib)
 list(APPEND link_libraries quantized_kernels quantized_ops_lib)
 
 if(EXECUTORCH_BUILD_KERNELS_CUSTOM)
-  list(APPEND link_libraries custom_ops)
+  list(APPEND link_libraries $<LINK_LIBRARY:WHOLE_ARCHIVE,custom_ops>)
 endif()
 
 set(XNNPACK_ROOT ${CMAKE_CURRENT_SOURCE_DIR}/../../../backends/xnnpack)