Examples on Metal use CPU - no GPU - and produce no output...or take minutes to execute --> MacOS M1 Max 64Gb

[oddpxl]

Describe the bug

High CPU use - no GPU use - MacOS 14.4.1 - Macbookpro M1 Max 64Gb

cargo build --example phi3v --release --features metal It takes minutes to execute the phiv3 on a small image - but I do get text output eventually.

or

cargo build --example gguf-locally --release --features metal

Output: general.architecture: llama general.file_type: 17 general.name: mistralai_mistral-7b-instruct-v0.1 general.quantization_version: 2 llama.attention.head_count: 32 llama.attention.head_count_kv: 8 llama.attention.layer_norm_rms_epsilon: 0.00001 llama.block_count: 32 llama.context_length: 32768 llama.embedding_length: 4096 llama.feed_forward_length: 14336 llama.rope.dimension_count: 128 llama.rope.freq_base: 10000

No output - just seems to keep crunching... ..killed it after 25min lol

Latest commit v0.1.24