powered by
Creates a context with automatically calculated size based on planned tensors.
ggml_init_auto(..., extra_mb = 10, type = GGML_TYPE_F32, no_alloc = FALSE)
GGML context
Named arguments with tensor dimensions (integer vectors)
Extra megabytes to add (default: 10)
Tensor type (default: GGML_TYPE_F32)
If TRUE, don't allocate memory for tensors (default: FALSE)
# \donttest{ ctx <- ggml_init_auto(mat1 = c(1000L, 1000L), mat2 = c(1000L, 1000L)) ggml_free(ctx) # }
Run the code above in your browser using DataLab