Donato Capitella
10 lines
806 B
Plaintext
10 lines
806 B
Plaintext
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
|
|
main: error: failed to create context with model '/home/kyuz0/models/qwen3-coder-30B-A3B/BF16/Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf'
|
|
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
|
|
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
|
|
✖ ! [rocm6_4_4] Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002__fa1 __longctx32768 failed (exit 0)
|