04b2771048
Performance (Qwen3-14B Q4_K_M, RX 9070 XT 16GB): - turbo4: 1812 pp512 / 49 tg128 / PPL +0.010 vs f16 / 72% KV savings - turbo3: 1836 pp512 / 50 tg128 / PPL +0.051 vs f16 / 78% KV savings - All context lengths up to 40K work without OOM Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>