Donato Capitella
10 lines
816 B
Plaintext
10 lines
816 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 | n_ubatch | fa | mmap | test | t/s |
|
|
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
|
|
| llama4 17Bx16E (Scout) Q8_0 | 106.65 GiB | 107.77 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 127.05 ± 0.00 |
|
|
HW Exception by GPU node-1 (Agent handle: 0x3beb7700) reason :GPU Hang
|
|
✖ ! [rocm7_rc-rocwmma] Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003 __fa1__longctx32768 failed (exit 134)
|