Loop id | Source Location | Source Function | Level | Max Thread Time / Walltime gcc_4 (%) | Exclusive Coverage gcc_4 (%) | Inclusive Coverage gcc_4 (%) | Max Exclusive Time Over Threads gcc_4 (s) | Max Inclusive Time Over Threads gcc_4 (s) | Exclusive Time w.r.t. Wall Time gcc_4 (s) | Inclusive Time w.r.t. Wall Time gcc_4 (s) | Nb Threads gcc_4 | Vectorization Ratio (%) | Vector Length Use (%) | Speedup If No Scalar Integer | Speedup If FP Vectorized | Speedup If Fully Vectorized | Speedup If Perfect Load Balancing gcc_4 | Stride 0 | Stride 1 | Stride n | Stride Unknown | Stride Indirect | Array Access Efficiency |
---|
2104 | libggml-cpu.so - quants.c:1089-1110 [...] | ggml_vec_dot_q8_0_q8_0 | Single | 74.45 | 78.97 | 78.97 | 13.98 | 13.98 | 14.03 | 14.03 | 64 | 64.52 | 35.08 | 1.13 | 1.13 | 2.77 | 1.02 | 0 | 1 | 3 | 2 | 0 | 70.83 |
1614 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.67 | 0.23 | 0.40 | 0.13 | 0.23 | 0.04 | 0.07 | 32 | 42.39 | 33.01 | 2.15 | 2.31 | 1.39 | 1.56 | NA | NA | NA | NA | NA | 0.00 |
75 | libggml-cpu.so - ggml-cpu.c:1664-2898 [...] | ggml_graph_compute_thread | Outermost | 0.32 | 0.17 | 0.32 | 0.06 | 0.13 | 0.03 | 0.06 | 63 | 0 | 18.75 | 1 | 1 | 8 | 2 | NA | NA | NA | NA | NA | 0.00 |
64 | libggml-cpu.so - ggml-cpu.c:1162-1198 [...] | ggml_compute_forward_mul_mat | InBetween | 0.35 | 0.17 | 0.17 | 0.06 | 0.06 | 0.03 | 0.03 | 64 | 0 | 28.18 | 1 | 1 | 2 | 2.25 | NA | NA | NA | NA | NA | 0.00 |
74 | libggml-cpu.so - ggml-cpu.c:2879-2898 [...] | ggml_graph_compute_thread | Innermost | 0.37 | 0.15 | 0.15 | 0.07 | 0.07 | 0.03 | 0.03 | 61 | 0 | 24.17 | 1 | 1 | 4.89 | 2.53 | NA | NA | NA | NA | NA | 0.00 |
788 | libggml-cpu.so - vec.cpp:311-311 [...] | ggml_vec_dot_f16 | Single | 0.45 | 0.14 | 0.14 | 0.09 | 0.09 | 0.03 | 0.03 | 32 | 100 | 66.67 | 1 | 1.7 | 1.35 | 1.69 | 0 | 0 | 4 | 6 | 0 | 60.00 |
2103 | libggml-cpu.so - quants.c:910-929 [...] | ggml_vec_dot_q8_0_q8_0 | Innermost | 0.21 | 0.14 | 0.14 | 0.04 | 0.04 | 0.02 | 0.02 | 64 | 70 | 36.88 | 1.17 | 1.14 | 2.73 | 1.67 | 0 | 2 | 0 | 0 | 0 | 100.00 |
1623 | libggml-cpu.so - vec.h:491-491 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.59 | 0.13 | 0.13 | 0.11 | 0.11 | 0.02 | 0.02 | 32 | 100 | 55.17 | 1 | 1.09 | 1.72 | 2.35 | 1 | 0 | 4 | 4 | 0 | 66.67 |
2087 | libggml-cpu.so - ggml-impl.h:354-404 [...] | quantize_row_q8_0 | Single | 0.29 | 0.12 | 0.12 | 0.05 | 0.05 | 0.02 | 0.02 | 63 | 32.32 | 23.78 | 1.07 | 1.28 | 2.13 | 2.7 | 1 | 2 | 0 | 0 | 0 | 100.00 |
820 | libggml-cpu.so - ops.cpp:6210-6245 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.19 | 0.07 | 0.07 | 0.04 | 0.04 | 0.01 | 0.01 | 58 | 2.22 | 13.47 | 1.66 | 1.48 | 7.75 | 2.65 | NA | NA | NA | NA | NA | 0.00 |
60 | libggml-cpu.so - ggml-cpu.c:1193-1194 | ggml_compute_forward_mul_mat | Innermost | 0.11 | 0.04 | 0.04 | 0.02 | 0.02 | 0.01 | 0.01 | 50 | 0 | 22.5 | 1 | 1 | 5.65 | 2.35 | 1 | 0 | 0 | 0 | 0 | 100.00 |
794 | libggml-cpu.so - vec.cpp:390-390 [...] | ggml_vec_swiglu_f32 | Innermost | 1.81 | 0.03 | 0.03 | 0.34 | 0.34 | 0.01 | 0.01 | 1 | 93.94 | 49.24 | 1.07 | 1.38 | 1.72 | 1 | 0 | 3 | 0 | 0 | 0 | 100.00 |
65 | libggml-cpu.so - ggml-cpu.c:1125-1397 [...] | ggml_compute_forward_mul_mat | Outermost | 0.16 | 0.03 | 0.27 | 0.03 | 0.08 | 0.01 | 0.05 | 33 | 0 | 50 | 1 | 1 | 2 | 2.91 | NA | NA | NA | NA | NA | 0.00 |
66 | libggml-cpu.so - ggml-cpu.c:1125-1395 [...] | ggml_compute_forward_mul_mat | Innermost | 0.11 | 0.03 | 0.03 | 0.02 | 0.02 | 0.01 | 0.01 | 37 | 0 | 28.06 | 1 | 1 | 2 | 2.31 | NA | NA | NA | NA | NA | 0.00 |
1613 | libggml-cpu.so - ops.cpp:8818-8826 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.13 | 0.02 | 0.02 | 0.03 | 0.03 | 0.00 | 0.00 | 24 | 0 | 21.43 | 10.67 | 1 | 8 | 2.5 | NA | NA | NA | NA | NA | 0.00 |
2102 | libggml-cpu.so - quants.c:908-1128 [...] | ggml_vec_dot_q8_0_q8_0 | Outermost | 0.11 | 0.02 | 0.16 | 0.02 | 0.05 | 0.00 | 0.03 | 32 | 30.56 | 25.69 | 1.6 | 1.71 | 5.24 | 2.91 | NA | NA | NA | NA | NA | 0.00 |
785 | libggml-cpu.so - vec.cpp:311-337 [...] | ggml_vec_dot_f16 | Outermost | 0.13 | 0.02 | 0.02 | 0.03 | 0.03 | 0.00 | 0.00 | 22 | 31.54 | 25.14 | 2.1 | 1.43 | 2.81 | 2.62 | NA | NA | NA | NA | NA | 0.00 |
1 | libggml-cpu.so - ggml-cpu.c:3228-3229 [...] | ggml_cpu_fp32_to_fp16 | Single | 0.24 | 0.01 | 0.01 | 0.05 | 0.05 | 0.00 | 0.00 | 13 | 100 | 51.72 | 1 | 1.04 | 2 | 4.33 | 2 | 0 | 0 | 0 | 0 | 100.00 |
72 | libggml-cpu.so - ggml-cpu.c:1290-1297 | ggml_compute_forward_mul_mat | InBetween | 0.08 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 22 | 0 | 26.81 | 1 | 1 | 2.02 | 2.44 | 1 | 0 | 0 | 1 | 0 | 75.00 |
1616 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.08 | 0.01 | 0.02 | 0.01 | 0.03 | 0.00 | 0.00 | 19 | 0 | 23.59 | 2.48 | 1.18 | 2.17 | 2.48 | NA | NA | NA | NA | NA | 0.00 |
830 | libggml-cpu.so - ops.cpp:6446-6457 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Innermost | 0.08 | 0.01 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 15 | 42.86 | 35.71 | 1 | 1 | 1.68 | 2.37 | 1 | 0 | 0 | 15 | 0 | 53.13 |
4449 | exec - sampling.cpp:125-126 [...] | common_sampler_sample(common_sampler*, llama_context*, int, bool) | Innermost | 0.48 | 0.01 | 0.01 | 0.09 | 0.09 | 0.00 | 0.00 | 1 | 16.13 | 16.13 | 1.5 | 1 | 8 | 1 | 0 | 0 | 2 | 9 | 0 | 54.55 |
815 | libggml-cpu.so - ops.cpp:6210-6475 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.05 | 0.01 | 0.08 | 0.01 | 0.04 | 0.00 | 0.01 | 13 | 0 | 16.2 | 2.04 | 1.59 | 6.84 | 1.62 | NA | NA | NA | NA | NA | 0.00 |
816 | libggml-cpu.so - ops.cpp:6210-6407 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.08 | 0.01 | 0.08 | 0.02 | 0.05 | 0.00 | 0.01 | 11 | 0.7 | 18.25 | 2.56 | 1.26 | 5.16 | 2.36 | NA | NA | NA | NA | NA | 0.00 |
515 | libggml-cpu.so - binary-ops.cpp:18-32 [...] | ggml_compute_forward_mul | Innermost | 0.32 | 0.01 | 0.01 | 0.06 | 0.06 | 0.00 | 0.00 | 1 | 100 | 50 | 1 | 1 | 2 | 1 | 0 | 0 | 3 | 0 | 0 | 75.00 |
1615 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | InBetween | 0.05 | 0.00 | 0.01 | 0.01 | 0.02 | 0.00 | 0.00 | 8 | 45.19 | 40.16 | 4.46 | 1.8 | 1.08 | 1.45 | NA | NA | NA | NA | NA | 0.00 |
1194 | libggml-cpu.so - ops.cpp:4325-4326 | ggml_compute_forward_rms_norm | Innermost | 0.24 | 0.00 | 0.00 | 0.05 | 0.05 | 0.00 | 0.00 | 1 | 100 | 48.89 | 1 | 1.25 | 2.22 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
431 | libggml-cpu.so - binary-ops.cpp:10-32 [...] | ggml_compute_forward_add_non_quantized | Innermost | 0.21 | 0.00 | 0.00 | 0.04 | 0.04 | 0.00 | 0.00 | 1 | 100 | 50 | 1 | 1 | 2 | 1 | 0 | 0 | 3 | 0 | 0 | 75.00 |
67 | libggml-cpu.so - ggml-cpu.c:1132-1165 [...] | ggml_compute_forward_mul_mat | Innermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 7 | 0 | 22.66 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
3551 | libllama.so - stl_algo.h:1594-1595 [...] | llama_token_data_array_partial_sort_inplace(llama_token_data_array*, int) | Innermost | 0.19 | 0.00 | 0.00 | 0.04 | 0.04 | 0.00 | 0.00 | 1 | 0 | 15.42 | 2.17 | 1 | 6.12 | 1 | 1.5 | 0.5 | 0.5 | 0 | 0 | 93.75 |
62 | libggml-cpu.so - ggml-cpu.c:1397-1397 | ggml_compute_forward_mul_mat | Innermost | 0.05 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 5 | NA | NA | NA | NA | NA | 1.67 | NA | NA | NA | NA | NA | 0.00 |
35 | libggml-base.so - ggml.c:1363-1388 [...] | ggml_is_contiguous_0 | Single | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 5 | 0 | 24.26 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
821 | libggml-cpu.so - ops.cpp:6210-6490 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | Outermost | 0.03 | 0.00 | 0.09 | 0.01 | 0.04 | 0.00 | 0.02 | 5 | 19.23 | 22.6 | 1.63 | 1.42 | 1.72 | 1 | NA | NA | NA | NA | NA | 0.00 |
817 | libggml-cpu.so - ops.cpp:6210-6439 [...] | ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool) | InBetween | 0.03 | 0.00 | 0.08 | 0.01 | 0.04 | 0.00 | 0.01 | 4 | 0 | 29.26 | 1 | 1 | 3 | 1 | NA | NA | NA | NA | NA | 0.00 |
73 | libggml-cpu.so - ggml-cpu.c:1289-1297 | ggml_compute_forward_mul_mat | Outermost | 0.03 | 0.00 | 0.01 | 0.01 | 0.01 | 0.00 | 0.00 | 3 | 0 | 35 | 1 | 1 | 3.11 | 1 | 1 | 0 | 0 | 1 | 0 | 75.00 |
1612 | libggml-cpu.so - ops.cpp:8778-8939 [...] | ggml_compute_forward_flash_attn_ext | Outermost | 0.03 | 0.00 | 0.40 | 0.00 | 0.12 | 0.00 | 0.07 | 3 | 0 | 15.38 | 3.22 | 1.34 | 7.48 | 1 | NA | NA | NA | NA | NA | 0.00 |
3913 | libllama.so - hashtable_policy.h:387-2058 [...] | llama_vocab::~llama_vocab() | Single | 0.08 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 4 | 1 | 0 | 0 | 0 | 2 | 0 | 50.00 |
4616 | libllama.so - hashtable.h:824-2079 [...] | std::_Hashtable<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, unsigned char>, s... | Outermost | 0.08 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0 | 36.72 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
3848 | libllama.so - basic_string.h:1077-3760 [...] | std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai... | Single | 0.08 | 0.00 | 0.00 | 0.02 | 0.02 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
103 | libggml-cpu.so - ggml-cpu.cpp:61-64 | ggml_backend_cpu_get_extra_buffer_types() | Single | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 3 | 0 | 50 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
238 | libggml-cpu.so - repack.cpp:1979-1982 | ggml_backend_cpu_repack_buffer_type() | Single | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 3 | 0 | 37.5 | 1 | 1 | 4 | 1 | NA | NA | NA | NA | NA | 0.00 |
334 | exec - stl_algobase.h:401-405 [...] | std::vector<std::__cxx11::sub_match<__gnu_cxx::__normal_iterator<char const*, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > >, std::allocator<std::__cxx11::sub_match<__gnu_cxx::__no... | Single | 0.05 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 18 | 1 | 1 | 5.65 | 1 | 0 | 0 | 3 | 2 | 0 | 65.00 |
1198 | libggml-cpu.so - vec.h:677-677 [...] | ggml_compute_forward_rms_norm | Innermost | 0.05 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 100 | 66.67 | 1 | 1.43 | 1.25 | 1 | 0 | 0 | 1 | 3 | 0 | 56.25 |
1618 | libggml-cpu.so - vec.h:677-677 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.05 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 100 | 66.67 | 1 | 1.43 | 1.25 | 1 | 0 | 0 | 1 | 3 | 0 | 56.25 |
37 | libggml-base.so - ggml.c:1365-1392 [...] | ggml_is_contiguous_1 | Innermost | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 26.25 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
4072 | libllama.so - llama-vocab.cpp:1575-2004 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | Outermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 24.34 | 1 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
4053 | libllama.so - llama-vocab.cpp:2312-2336 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | Outermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 3.77 | 19.4 | 2.67 | 1 | 10.24 | 1 | NA | NA | NA | NA | NA | 0.00 |
4060 | libllama.so - llama-vocab.cpp:2148-2289 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | Single | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 6.2 | 18.14 | 2.75 | 1 | 16.47 | 1 | NA | NA | NA | NA | NA | 0.00 |
1274 | libggml-cpu.so - ops.cpp:5330-5517 [...] | ggml_compute_forward_get_rows | Outermost | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 0 | 38.47 | 1 | 1 | 1.5 | 1 | NA | NA | NA | NA | NA | 0.00 |
1694 | libllama.so - basic_string.h:218-1077 [...] | replace_all(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<... | Innermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 26.88 | 1 | 1 | 5.05 | 1 | NA | NA | NA | NA | NA | 0.00 |
4211 | libllama.so - basic_string.h:1077-3760 [...] | std::__detail::_Map_base<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, int>, st... | Single | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 2 | 1 | 0.67 | 0 | 0 | 2 | 0 | 61.11 |
40 | libggml-base.so - ggml.c:1444-1448 | ggml_are_same_shape | Single | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 21.88 | 1 | 1 | 6 | 1 | NA | NA | NA | NA | NA | 0.00 |
3438 | libllama.so - stl_heap.h:229-235 | void std::__adjust_heap<llama_token_data*, long, llama_token_data, __gnu_cxx::__ops::_Iter_comp_iter<llama_token_data_array_partial_sort_inplace(llama_token_data_array*, int)::{lambda(llama_token_data const&, llama_token_data const&)#1}> &... | Single | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 20.16 | 1 | 1 | 6.03 | 1 | 0 | 0 | 0 | 2.5 | 1 | 35.42 |
36 | libggml-base.so - ggml.c:1363-1392 [...] | ggml_is_contiguous_1 | Outermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 4.27 | 1 | NA | NA | NA | NA | NA | 0.00 |
1192 | libggml-cpu.so - ops.cpp:4319-4351 [...] | ggml_compute_forward_rms_norm | InBetween | 0.03 | 0.00 | 0.01 | 0.01 | 0.06 | 0.00 | 0.00 | 1 | 52.02 | 43.5 | 1.71 | 1.96 | 1.56 | 1 | NA | NA | NA | NA | NA | 0.00 |
1196 | libggml-cpu.so - ops.cpp:4319-4365 [...] | ggml_compute_forward_rms_norm | Outermost | 0.03 | 0.00 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | NA | NA | NA | NA | NA | 1 | NA | NA | NA | NA | NA | 0.00 |
392 | libggml-cpu.so - binary-ops.cpp:10-146 [...] | ggml_compute_forward_add_non_quantized | InBetween | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 1.56 | 34.18 | 11.43 | 1 | 2 | 1 | NA | NA | NA | NA | NA | 0.00 |
4239 | libllama.so - hashtable.h:2627-2644 [...] | std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai... | Innermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 25 | 1 | 1 | 2 | 1 | 0 | 0 | 0 | 4 | 1 | 40.00 |
3944 | libllama.so - basic_string.h:223-1576 [...] | llama_vocab::impl::token_to_piece(int, char*, int, int, bool) const | Innermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 21.38 | 1 | 1 | 9.21 | 1 | NA | NA | NA | NA | NA | 0.00 |
1692 | libllama.so - llama-impl.cpp:73-76 [...] | replace_all(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<... | Innermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 27.63 | 1 | 1 | 4 | 1 | 4 | 0 | 0 | 0 | 0 | 100.00 |
1282 | libggml-cpu.so - ops.cpp:5551-5563 | ggml_compute_forward_set_rows | InBetween | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 29.82 | 1 | 1 | 2.22 | 1 | NA | NA | NA | NA | NA | 66.67 |
1905 | libllama.so - stl_algobase.h:951-952 | llama_kv_cache::set_input_kq_mask(ggml_tensor*, llama_ubatch const*, bool) const | Single | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 100 | 88.89 | 1 | 1 | 1.13 | 1 | 0 | 0 | 1 | 1 | 0 | 62.50 |
4238 | libllama.so - hashtable.h:2627-2644 [...] | std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai... | InBetween | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | NA | NA | 1 | NA | NA | 1 | NA | NA | NA | NA | NA | 0.00 |
1621 | libggml-cpu.so - ops.cpp:8885-8886 [...] | ggml_compute_forward_flash_attn_ext | Innermost | 0.03 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1 | 100 | 56.25 | 1 | 1 | 1.64 | 1 | 0 | 0 | 2 | 2 | 0 | 62.50 |
297 | libggml-base.so - ggml-impl.h:192-297 [...] | ggml_backend_sched_split_graph | Innermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 20.31 | 1 | 1 | 2.3 | 1 | 0 | 0 | 0 | 0 | 2 | 0.00 |
4054 | libllama.so - char_traits.h:381-381 [...] | llama_vocab::impl::load(llama_model_loader&, LLM_KV const&) | Single | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 11.11 | 18.29 | 3 | 1 | 10.91 | 1 | NA | NA | NA | NA | NA | 0.00 |
1719 | libggml-cpu.so - ops.cpp:3433-9815 [...] | ggml_compute_forward_glu | Outermost | 0.03 | 0.00 | 0.00 | 0.01 | 0.01 | 0.00 | 0.00 | 1 | 0 | 24.49 | 1 | 1 | 1.25 | 1 | NA | NA | NA | NA | NA | 0.00 |