ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
| model                          |       size |     params | backend    | ngl | n_ubatch | fa | mmap |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
| glm4moe 106B.A12B Q4_K - Medium |  68.01 GiB |   110.47 B | ROCm       |  99 |     2048 |  1 |    0 | pp2048 @ d32768 |         17.23 ± 0.00 |
Memory access fault by GPU node-1 (Agent handle: 0x15b288c0) on address 0x7f4ebb38d000. Reason: Page not present or supervisor privilege.
✖ ! [rocm7.1-rocwmma] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 __hblt0__fa1__longctx32768 failed (exit 134)