Failed to create llama_context

[samkirubakaranl]

Hi,

I have followed all the Installation steps as given but I am facing below error
self._ctx = _LlamaContext(
^^^^^^^^^^^^^^
File "/Users/User1/Desktop/personalGPT/privateGPT/local_env/lib/python3.11/site-packages/llama_cpp/_internals.py", line 275, in init
raise ValueError("Failed to create llama_context")
ValueError: Failed to create llama_conte

Also, i see lot of below errors

    ^~~~~~~~~~~~~~~~~~~~~~~~~~~

program_source:8261:22: note: type 'int64_t' (aka 'long') cannot be used in buffer pointee type
constant int64_t & ne11,

program_source:7985:21: note: type 'uint64_t' (aka 'unsigned long') cannot be used in buffer pointee type
constant uint64_t & nb1,
^
program_source:8060:12: error: 'host_name' attribute requires Metal language standard macos-metal2.2 or higher
template [[host_name("kernel_get_rows_q4_0")]] kernel get_rows_t kernel_get_rows<block_q4_0, 2, dequantize_q4_0>;
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:8061:12: error: 'host_name' attribute requires Metal language standard macos-metal2.2 or higher
template [[host_name("kernel_get_rows_q4_1")]] kernel get_rows_t kernel_get_rows<block_q4_1, 2, dequantize_q4_1>;
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:8062:12: error: 'host_name' attribute requires Metal language standard macos-metal2.2 or higher
template [[host_name("kernel_get_rows_q5_0")]] kernel get_rows_t kernel_get_rows<block_q5_0, 2, dequantize_q5_0>;
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:8063:12: error: 'host_name' attribute requires Metal language standard macos-metal2.2 or higher
template [[host_name("kernel_get_rows_q5_1")]] kernel get_rows_t kernel_get_rows<block_q5_1, 2, dequantize_q5_1>;
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:8064:12: error: 'host_name' attribute requires Metal language standard macos-metal2.2 or higher
template [[host_name("kernel_get_rows_q8_0")]] kernel get_rows_t kernel_get_rows<block_q8_0, 2, dequantize_q8_0>;
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Could someone please help me on this ?