ggml_metal_library_compile_pipeline: failed to compile pipeline: for LFM2-8B-A1B-Q8_0.gguf

[leok7v]

https://github.com/ggml-org/llama.cpp/blob/master/ggml/src/ggml-metal/ggml-metal.metal#L8912
Invokes templates:

template [[host_name("kernel_mul_mm_id_map0_ne20_1" )]] kernel kernel_mul_mm_id_map0_t kernel_mul_mm_id_map0<1>;
template [[host_name("kernel_mul_mm_id_map0_ne20_2" )]] kernel kernel_mul_mm_id_map0_t kernel_mul_mm_id_map0<2>;
template [[host_name("kernel_mul_mm_id_map0_ne20_4" )]] kernel kernel_mul_mm_id_map0_t kernel_mul_mm_id_map0<4>;
template [[host_name("kernel_mul_mm_id_map0_ne20_6" )]] kernel kernel_mul_mm_id_map0_t kernel_mul_mm_id_map0<6>;
template [[host_name("kernel_mul_mm_id_map0_ne20_8" )]] kernel kernel_mul_mm_id_map0_t kernel_mul_mm_id_map0<8>;
template [[host_name("kernel_mul_mm_id_map0_ne20_10")]] kernel kernel_mul_mm_id_map0_t kernel_mul_mm_id_map0<10>;
template [[host_name("kernel_mul_mm_id_map0_ne20_16")]] kernel kernel_mul_mm_id_map0_t kernel_mul_mm_id_map0<16>;

While model:
https://huggingface.co/LiquidAI/LFM2-8B-A1B-GGUF/resolve/main/LFM2-8B-A1B-Q8_0.gguf
from
https://huggingface.co/LiquidAI/LFM2-8B-A1B-GGUF
is using kernel_mul_mm_id_map0_ne20_32_ne02 and failing to compile

Looks like it is coming from commit:

0320ac5#r171605769

See discussion Q&A here:

#17591