add missing cmake flags to build llama runner for android (#3611)

Summary:
This PR fixes the android build failure for llama3-instruct https://github.com/pytorch/executorch/issues/3601

The cmake flags
```
-DEXECUTORCH_BUILD_XNNPACK=ON
-DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON
-DEXECUTORCH_BUILD_KERNELS_QUANTIZED=ON
-DEXECUTORCH_BUILD_KERNELS_CUSTOM=ON
```
are missing in the Llama's readme when building executorch and llama runner for android.
`-DEXECUTORCH_BUILD_KERNELS_CUSTOM=ON` is required, otherwise the model fails during runtime.

Tested and verified on a Samsung S23.

```
(executorch) salykova@xmachine ~/Projects/executorch (main) $ adb shell "cd /data/local/tmp/llama && ./llama_main --model_path /data/local/tmp/llama/llama3_kv_sdpa_xnn_qe_4_32.pte --tokenizer_path /data/local/tmp/llama/tokenizer.bin --prompt '<|begin_of_text|> <|start_header_id|>User<|end_header_id|>Why is Pytorch so fast?<|eot_id|>' --seq_len 256"
I 00:00:00.011654 executorch:cpuinfo_utils.cpp:61] Reading file /sys/devices/soc0/image_version
I 00:00:00.012361 executorch:main.cpp:65] Resetting threadpool with num threads = 4
I 00:00:00.021018 executorch:runner.cpp:54] Creating LLaMa runner: model_path=/data/local/tmp/llama/llama3_kv_sdpa_xnn_qe_4_32.pte, tokenizer_path=/data/local/tmp/llama/tokenizer.bin
I 00:00:05.708101 executorch:runner.cpp:69] Reading metadata from model
I 00:00:05.708208 executorch:runner.cpp:134] get_vocab_size: 128256
I 00:00:05.708228 executorch:runner.cpp:134] get_bos_id: 128000
I 00:00:05.708244 executorch:runner.cpp:134] get_eos_id: 128001
I 00:00:05.708259 executorch:runner.cpp:134] get_n_bos: 1
I 00:00:05.708274 executorch:runner.cpp:134] get_n_eos: 1
I 00:00:05.708293 executorch:runner.cpp:134] get_max_seq_len: 128
I 00:00:05.708308 executorch:runner.cpp:134] use_kv_cache: 1
I 00:00:05.708324 executorch:runner.cpp:134] use_sdpa_with_kv_cache: 1
I 00:00:05.708339 executorch:runner.cpp:134] append_eos_to_prompt: 0
<|begin_of_text|> <|start_header_id|>User<|end_header_id|>Why is Pytorch so fast?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

PyTorch is considered fast for several reasons:

1. **Just-In-Time (JIT) compilation**: PyTorch has a built-in JIT compiler that can compile PyTorch models into optimized machine code at runtime. This allows PyTorch to skip the overhead of interpreted Python code and execute the model directly on the CPU or GPU, making it faster and more efficient.
2. **Autograd**: PyTorch's autograd system automatically calculates gradients, which is a crucial component of backpropagation. This means that PyTorch canI 00:00:22.615399 executorch:runner.cpp:419]         Prompt Tokens: 14    Generated Tokens: 113
I 00:00:22.615425 executorch:runner.cpp:425]    Model Load Time:                6.028000 (seconds)
I 00:00:22.615450 executorch:runner.cpp:435]    Total inference time:           16.564000 (seconds)              Rate:  6.822024 (tokens/second)
I 00:00:22.615465 executorch:runner.cpp:443]            Prompt evaluation:      1.420000 (seconds)               Rate:  9.859155 (tokens/second)
I 00:00:22.615485 executorch:runner.cpp:454]            Generated 113 tokens:   15.144000 (seconds)              Rate:  7.461701 (tokens/second)
I 00:00:22.615501 executorch:runner.cpp:462]    Time to first generated token:  1.522000 (seconds)
I 00:00:22.615514 executorch:runner.cpp:469]    Sampling time over 127 tokens:  0.281000 (seconds)

PyTorchObserver {"prompt_tokens":14,"generated_tokens":113,"model_load_start_ms":1715721953250,"model_load_end_ms":1715721959278,"inference_start_ms":1715721959278,"inference_end_ms":1715721975842,"prompt_eval_end_ms":1715721960698,"first_token_ms":1715721960800,"aggregate_sampling_time_ms":281,"SCALING_FACTOR_UNITS_PER_SECOND":1000}
```

Pull Request resolved: https://github.com/pytorch/executorch/pull/3611

Reviewed By: mergennachin

Differential Revision: D57367223

Pulled By: kimishpatel

fbshipit-source-id: 64cbaf6f1e5eddac8d71d4cd7b9fe09c8ebec478