Donato Capitella
25 lines
1.7 KiB
Plaintext
25 lines
1.7 KiB
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
|
|
| model | size | params | backend | ngl | fa | test | t/s |
|
|
| ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: |
|
|
/opt/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:90: ROCm error
|
|
/usr/local/lib64/libggml-base.so.0(+0x3565) [0x7f10ce59f565]
|
|
/usr/local/lib64/libggml-base.so.0(ggml_print_backtrace+0x1eb) [0x7f10ce59f92b]
|
|
/usr/local/lib64/libggml-base.so.0(ggml_abort+0x11f) [0x7f10ce59faaf]
|
|
/usr/local/lib64/libggml-hip.so.0(+0x2eb0be2) [0x7f10d150cbe2]
|
|
/usr/local/lib64/libggml-hip.so.0(+0x2eb5d59) [0x7f10d1511d59]
|
|
/usr/local/lib64/libggml-base.so.0(ggml_backend_sched_graph_compute_async+0x36d) [0x7f10ce5b99dd]
|
|
/usr/local/lib64/libllama.so.0(_ZN13llama_context13graph_computeEP11ggml_cgraphb+0xa0) [0x7f10d1bcb990]
|
|
/usr/local/lib64/libllama.so.0(_ZN13llama_context14process_ubatchERK12llama_ubatch14llm_graph_typeP22llama_memory_context_iR11ggml_status+0xe2) [0x7f10d1bcd622]
|
|
/usr/local/lib64/libllama.so.0(_ZN13llama_context6decodeERK11llama_batch+0x3bf) [0x7f10d1bd24df]
|
|
/usr/local/lib64/libllama.so.0(llama_decode+0xe) [0x7f10d1bd32fe]
|
|
/usr/local/bin/llama-bench() [0x40abdb]
|
|
/usr/local/bin/llama-bench() [0x40898d]
|
|
/lib64/libc.so.6(+0x35b5) [0x7f10cdf355b5]
|
|
/lib64/libc.so.6(__libc_start_main+0x88) [0x7f10cdf35668]
|
|
/usr/local/bin/llama-bench() [0x409a75]
|
|
✖ ! [rocm7.1-rocwmma] gemma-3-27b-it-BF16-00001-of-00002__fa1 failed (exit 0)
|