Donato Capitella
10 lines
804 B
Plaintext
10 lines
804 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 |
|
|
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
|
|
| glm4moe 106B.A12B Q4_K - Medium | 68.01 GiB | 110.47 B | ROCm | 99 | 2048 | 1 | 0 | pp2048 @ d32768 | 16.40 ± 0.00 |
|
|
HW Exception by GPU node-1 (Agent handle: 0x1678a6f0) reason :GPU Hang
|
|
✖ ! [rocm7_rc-rocwmma] GLM-4.5-Air-UD-Q4_K_XL-00001-of-00002 __fa1__longctx32768 failed (exit 134)
|