Files
amd-strix-halo-toolboxes/benchmark/results_old/Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002__rocm7_beta.log
T
2025-08-09 10:44:09 +01:00

7 lines
354 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
HW Exception by GPU node-1 (Agent handle: 0xa5e9440) reason :GPU Hang
✖ ! [rocm7_beta] Llama-3.3-70B-Instruct-UD-Q8_K_XL-00001-of-00002 failed (exit 134)