Files
amd-strix-halo-toolboxes/benchmark/results/gpt-oss-120b-F16__rocm6_4_4-rocwmma__hblt0__fa1.log
T
Donato Capitella 67fb3a002b Updated benchmarks
2025-11-15 08:36:25 +00:00

11 lines
803 B
Plaintext

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 |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
| gpt-oss 120B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | pp512 | 783.56 ± 11.04 |
| gpt-oss 120B F16 | 60.87 GiB | 116.83 B | ROCm | 99 | 2048 | 1 | 0 | tg128 | 37.18 ± 0.01 |
build: 1c398dc9e (7034)