kazeia

Commit Graph

Author	SHA1	Message	Date
Kazeia Team	8bfe6c7445	Add NEON SIMD heads argmax for CP — 2.3× speedup CP head dot products (15 × 2048×1024) optimized with ARM NEON vfmaq_f32 (4 accumulators, 16 floats/iteration). CP/frame: 131ms → 58ms, total pipeline: 22.7s → 14.7s (RTF 3.2) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-09 08:55:20 +02:00
Kazeia Team	389ffa7c61	Initial commit: Kazeia TTS pipeline on NPU via ExecuTorch Full Qwen3-TTS-0.6B pipeline running on Snapdragon 8 Elite NPU: - Talker (28L) and Code Predictor (5L) as .pte on QNN HTP fp16 - JNI integration, no root required - Validated audio quality: RTF 3.9 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-09 08:42:11 +02:00

Author

SHA1

Message

Date

Kazeia Team

8bfe6c7445

Add NEON SIMD heads argmax for CP — 2.3× speedup

CP head dot products (15 × 2048×1024) optimized with ARM NEON
vfmaq_f32 (4 accumulators, 16 floats/iteration).

CP/frame: 131ms → 58ms, total pipeline: 22.7s → 14.7s (RTF 3.2)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-09 08:55:20 +02:00

Kazeia Team

389ffa7c61

Initial commit: Kazeia TTS pipeline on NPU via ExecuTorch

Full Qwen3-TTS-0.6B pipeline running on Snapdragon 8 Elite NPU:
  - Talker (28L) and Code Predictor (5L) as .pte on QNN HTP fp16
  - JNI integration, no root required
  - Validated audio quality: RTF 3.9

  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-09 08:42:11 +02:00

2 Commits