Loadtest Cuda

Standalone load-test for src/model/loader_cuda.zig.

Drives only the CUDA loader path: select the best device, mmap + parse a GGUF, upload every tensor to the GPU, and report the parsed config, the tensor count, GPU free-mem before/after (to confirm ~model-size uploaded), a spot-check of 3 tensors, and a CPU embedding-row dequant. Independent of forward_cuda / gpu dispatch so the loader can be validated on its own.

Rooted at src/ (module path) so it can import both model/* and cuda/* — exactly like src/main.zig. The whole thing is one Zig module, which keeps the loader's internal `../cuda/*` imports resolvable.

Build + run (on the box): cd ~/zinc5090 && CUDA_HOME=/usr/local/cuda \ ~/zig-0.15.2/zig build cuda-loadtest -Dbackend=cuda -- <model.gguf>

1 exports 0 methods src/loadtest_cuda.zig

1 exports shown

function

main

pub fn main() !void

Load a GGUF onto the GPU via loader_cuda and print a structured report.

surfaces a nonzero exit on failure.

Returns

Propagates loader errors (init/open/parse/upload) so the build step

src/loadtest_cuda.zig:26