Kazeia Team 14f7e5b05f Optimize CP+talker: eliminate prepare_input_tensors per step ... Cache input tensor pointers after first prepare_input_tensors call, then memcpy directly into them for all subsequent steps. Eliminates ~14000 mallocs per pipeline run (986 CP + 58 talker calls). Generation: 4640ms → 4007ms (-633ms), total RTF: 1.6 → 1.51 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>		2026-04-09 12:16:38 +02:00
..
Module.java	Shared Module C++ pipeline: RTF 1.6 with perfect quality	2026-04-09 12:05:58 +02:00
cp_et_runner.cpp	Native C++ pipeline: RTF 1.4 (was 3.6 in Java)	2026-04-09 10:09:32 +02:00
cp_et_test_client.cpp	Native C++ pipeline: RTF 1.4 (was 3.6 in Java)	2026-04-09 10:09:32 +02:00
jni_layer_tts.cpp	Optimize CP+talker: eliminate prepare_input_tensors per step	2026-04-09 12:16:38 +02:00
tts_pipeline_jni.cpp	Disable C++ pipeline (QNN non-deterministic), keep Java RTF 1.8	2026-04-09 11:42:49 +02:00