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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |     2048 |  1 |    0 |           pp512 |        103.28 ± 0.10 |
| llama 70B Q8_0                 |  75.65 GiB |    70.55 B | ROCm       |  99 |     2048 |  1 |    0 |           tg128 |          2.79 ± 0.00 |

build: ee8dd5c65 (7035)