Donato Capitella
21 lines
1.3 KiB
Plaintext
21 lines
1.3 KiB
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: Radeon 8060S Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
|
| model | size | params | backend | ngl | n_ubatch | fa | mmap | test | t/s |
|
|
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | ---: | --------------: | -------------------: |
|
|
/opt/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:89: ROCm error
|
|
/usr/local/lib64/libggml-base.so.0(+0x3565) [0x7f056f2a5565]
|
|
/usr/local/lib64/libggml-base.so.0(ggml_print_backtrace+0x1eb) [0x7f056f2a592b]
|
|
/usr/local/lib64/libggml-base.so.0(ggml_abort+0x11f) [0x7f056f2a5aaf]
|
|
/usr/local/lib64/libggml-hip.so.0(+0x28bcf12) [0x7f0571c1ef12]
|
|
/usr/local/lib64/libggml-hip.so.0(+0x28c1f64) [0x7f0571c23f64]
|
|
/usr/local/lib64/libggml-base.so.0(ggml_backend_sched_synchronize+0x2e) [0x7f056f2bc8ce]
|
|
/usr/local/lib64/libllama.so.0(_ZN13llama_context11synchronizeEv+0x10) [0x7f05722f1950]
|
|
/usr/local/bin/llama-bench() [0x40a3fc]
|
|
/usr/local/bin/llama-bench() [0x40816d]
|
|
/lib64/libc.so.6(+0x35b5) [0x7f056ec3b5b5]
|
|
/lib64/libc.so.6(__libc_start_main+0x88) [0x7f056ec3b668]
|
|
/usr/local/bin/llama-bench() [0x409255]
|
|
✖ ! [rocm-7alpha] llama-2-7b.Q4_0__hblt0__fa1 __longctx32768 failed (exit 0)
|