kazeia/kazeia-android/app
Kazeia Team a688edc9ec Reduce talker KV_LEN 100→64: saves 148ms (RTF 1.31)
KV window of 64 sufficient for ~70 token generation (10 prefill + 58 gen).
36% less KV memcpy per talker step (28L × 2 × 64×8×128 vs 100×8×128).

Generation: 3795ms → 3647ms, total: 6438ms → 6093ms

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-09 12:47:30 +02:00
..
src/main Reduce talker KV_LEN 100→64: saves 148ms (RTF 1.31) 2026-04-09 12:47:30 +02:00
build.gradle.kts Initial commit: Kazeia TTS pipeline on NPU via ExecuTorch 2026-04-09 08:42:11 +02:00
proguard-rules.pro Initial commit: Kazeia TTS pipeline on NPU via ExecuTorch 2026-04-09 08:42:11 +02:00