25 lines
1.8 KiB
Plaintext
25 lines
1.8 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 | n_ubatch | fa | test | t/s |
|
||
|
|
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
|
||
|
|
/opt/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:92: ROCm error
|
||
|
|
/usr/local/lib64/libggml-base.so.0(+0x3565) [0x7fa9d6d2f565]
|
||
|
|
/usr/local/lib64/libggml-base.so.0(ggml_print_backtrace+0x1eb) [0x7fa9d6d2f92b]
|
||
|
|
/usr/local/lib64/libggml-base.so.0(ggml_abort+0x11f) [0x7fa9d6d2faaf]
|
||
|
|
/usr/local/lib64/libggml-hip.so.0(+0x2da2e22) [0x7fa9d9b8ee22]
|
||
|
|
/usr/local/lib64/libggml-hip.so.0(+0x2da7f39) [0x7fa9d9b93f39]
|
||
|
|
/usr/local/lib64/libggml-base.so.0(ggml_backend_sched_graph_compute_async+0x36d) [0x7fa9d6d49add]
|
||
|
|
/usr/local/lib64/libllama.so.0(_ZN13llama_context13graph_computeEP11ggml_cgraphb+0xa0) [0x7fa9da258a90]
|
||
|
|
/usr/local/lib64/libllama.so.0(_ZN13llama_context14process_ubatchERK12llama_ubatch14llm_graph_typeP22llama_memory_context_iR11ggml_status+0xe2) [0x7fa9da25a722]
|
||
|
|
/usr/local/lib64/libllama.so.0(_ZN13llama_context6decodeERK11llama_batch+0x3bf) [0x7fa9da25f5df]
|
||
|
|
/usr/local/lib64/libllama.so.0(llama_decode+0xe) [0x7fa9da2603fe]
|
||
|
|
/usr/local/bin/llama-bench() [0x40acdb]
|
||
|
|
/usr/local/bin/llama-bench() [0x4087ec]
|
||
|
|
/lib64/libc.so.6(+0x35b5) [0x7fa9d66c55b5]
|
||
|
|
/lib64/libc.so.6(__libc_start_main+0x88) [0x7fa9d66c5668]
|
||
|
|
/usr/local/bin/llama-bench() [0x409b65]
|
||
|
|
✖ ! [rocm-7-nightly] gemma-3-27b-it-BF16-00001-of-00002__fa1 __longctx16384 failed (exit 0)
|