ggml_metal_get_buffer about h2ogpt HOT 3 OPEN

ggml_metal_add_buffer: allocated 'kv ' buffer, size = 512.03 MiB, ( 4458.33 / 4096.00)ggml_metal_add_buffer: warning: current allocated size is greater than the recommended max working set size
ggml_metal_add_buffer: allocated 'alloc ' buffer, size = 576.01 MiB, ( 5034.34 / 4096.00)ggml_metal_add_buffer: warning: current allocated size is greater than the recommended max working set size
AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 |
ggml_metal_get_buffer: error: buffer is nil

from h2ogpt.

I'm not sure what this means, something wrong with the Metal build of llama_cpp_python

from h2ogpt.

@rdhillbb

1. What is the model you are trying to run with h2ogpt?
2. How are you using h2ogpt? using a one-click installer or built manually?

from h2ogpt.