2025-12-07 16:57:56 +00:00
|
|
|
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 Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
|
|
|
|
|
Device 1: AMD Radeon Graphics, gfx1201 (0x1201), VMM: no, Wave Size: 32
|
|
|
|
|
| model | size | params | backend | ngl | n_ubatch | fa | test | t/s |
|
|
|
|
|
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | -: | --------------: | -------------------: |
|
2025-12-17 08:01:12 +00:00
|
|
|
/opt/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:94: ROCm error
|
|
|
|
|
/usr/local/lib64/libggml-base.so.0(+0x35a5) [0x7f5ce064e5a5]
|
|
|
|
|
/usr/local/lib64/libggml-base.so.0(ggml_print_backtrace+0x1eb) [0x7f5ce064e96b]
|
|
|
|
|
/usr/local/lib64/libggml-base.so.0(ggml_abort+0x11f) [0x7f5ce064eaef]
|
|
|
|
|
/usr/local/lib64/libggml-hip.so.0(+0x30a69b2) [0x7f5ce37b19b2]
|
|
|
|
|
/usr/local/lib64/libggml-hip.so.0(+0x30abad9) [0x7f5ce37b6ad9]
|
|
|
|
|
/usr/local/lib64/libggml-base.so.0(ggml_backend_sched_graph_compute_async+0x36d) [0x7f5ce0668ffd]
|
|
|
|
|
/usr/local/lib64/libllama.so.0(_ZN13llama_context13graph_computeEP11ggml_cgraphb+0xa0) [0x7f5ce3e887e0]
|
|
|
|
|
/usr/local/lib64/libllama.so.0(_ZN13llama_context14process_ubatchERK12llama_ubatch14llm_graph_typeP22llama_memory_context_iR11ggml_status+0xe2) [0x7f5ce3e8a2b2]
|
|
|
|
|
/usr/local/lib64/libllama.so.0(_ZN13llama_context6decodeERK11llama_batch+0x3bf) [0x7f5ce3e8f6ff]
|
|
|
|
|
/usr/local/lib64/libllama.so.0(llama_decode+0xe) [0x7f5ce3e904fe]
|
|
|
|
|
/usr/local/bin/llama-bench() [0x40ad9b]
|
|
|
|
|
/usr/local/bin/llama-bench() [0x408b3d]
|
|
|
|
|
/lib64/libc.so.6(+0x35b5) [0x7f5cdffe45b5]
|
|
|
|
|
/lib64/libc.so.6(__libc_start_main+0x88) [0x7f5cdffe4668]
|
|
|
|
|
/usr/local/bin/llama-bench() [0x409c25]
|
2025-12-07 16:57:56 +00:00
|
|
|
✖ ! [rocm-7.9] gemma-3-27b-it-BF16-00001-of-00002__fa1 __longctx32768 failed (exit 0)
|
