lixiang c3263bd618 Add M5 Max benchmark — first H17 ANE on record ... _ANEDeviceInfo.aneSubType returns "h17" on M5 Max (M4 / base M5 = "h16"), but peak FP16 (19.27 TFLOPS) and INT8 W8A8 (35.61 TOPS) match M4 within 4%. Stories110M static 90.0 ms/step, dynamic 73.5 ms/step; Qwen3-0.6B dynamic 320.0 ms/step (1.29× M4 baseline). Training gains over base M5 are CPU-driven (12 P-cores + Accelerate), not ANE-driven. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>		2026-04-23 17:18:52 +08:00
..
ANE_BENCHMARK_REPORT.md	Add model config to benchmark report, update README with current results	2026-03-04 06:13:21 -08:00
community_results.json	Add M5 Max benchmark — first H17 ANE on record	2026-04-23 17:18:52 +08:00
m5max_result.md	Add M5 Max benchmark — first H17 ANE on record	2026-04-23 17:18:52 +08:00