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: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32 | model | size | params | backend | ngl | fa | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: | | mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | pp512 | 2312.05 ± 24.53 | | mistral3 14B BF16 | 25.16 GiB | 13.51 B | ROCm | 99 | 1 | tg128 | 19.86 ± 0.03 | build: 6016d0bd4 (7285)