Donato Capitella
11 lines
756 B
Plaintext
11 lines
756 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: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
|
| model | size | params | backend | ngl | fa | mmap | test | t/s |
|
|
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | ---: | --------------: | -------------------: |
|
|
| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | pp512 | 1100.05 ± 4.01 |
|
|
| llama 7B Q4_0 | 3.56 GiB | 6.74 B | ROCm | 99 | 1 | 0 | tg128 | 49.29 ± 0.01 |
|
|
|
|
build: f1fbffb5 (6486)
|