Files

12 lines
811 B
Plaintext
Raw Permalink Normal View History

2025-12-07 10:27:33 +00:00
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
Device 1: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32
| model | size | params | backend | ngl | fa | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
2025-12-17 08:01:12 +00:00
| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | pp512 | 1739.63 ± 90.44 |
| gpt-oss 120B MXFP4 MoE | 59.02 GiB | 116.83 B | ROCm | 99 | 1 | tg128 | 92.08 ± 0.55 |
build: 2aa45ef9e (7423)