nullname c23ab465c0 feat: perf opt part4 (#43) ... * wip * refactor: rewrite dequantize_row_q4_0 by intrinsic * log for debug * fix q4 intrinsic * small opt * wip * wip * add vtcm_quota_size * add perf log for hexagon-npu backend * wip * add log * sync after a specfic op * increase worker thread priority * fix unbalanced thread slice * small slict to fit in vtcm cache * limit the supported row element size * opt 4_0 dequant * fix q4 dequant * add power_utils * add rms_norm * wip * enable rms_norm f32 * fix rms_norm with param * fix compiling flags * use float * fix small row size * vectorized rms norm * wip * read 2 vectors * rename * add perf log on update * set empty tensors handle also * merge some rpc functions * opt param update * wip * print more log * add struct for update param config * add npu_device_graph_set_tensor_with_param * merge tensor and params update * wip * wip * make as template to reuse * vectorize dequantize_row_q8_0 * opt * avoid using union to store q data * wip * wip * wip		2025-05-28 00:00:42 +08:00
..
device.cpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
graph.cpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
graph.hpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
op_impl.cpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
op_impl.hpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
op_mul_mat.cpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
op_mul_mat.hpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
op_types.hpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
quants.cpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
quants.hpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
tensor.hpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
thread_pool.hpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
util.hpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00
vtcm_mem.hpp	feat: perf opt part4 (#43)	2025-05-28 00:00:42 +08:00