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 Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32 | model | size | params | backend | ngl | mmap | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | ---: | --------------: | -------------------: | | gpt-oss ?B F16 | 60.87 GiB | 116.83 B | ROCm | 999 | 0 | pp512 | 592.27 ± 5.61 | | gpt-oss ?B F16 | 60.87 GiB | 116.83 B | ROCm | 999 | 0 | tg128 | 33.68 ± 0.02 | build: 34c9d765 (6122)