{"model":"deepseek-4.1-flash","title":"PP6 adopted as the PP default (validated)","status":"positive","summary":"PP6 (TP1xPP6, partition 7,7,7,7,7,5, util 0.95) now served: c1 96.9 best-of-4 (107.6 with 93.8% DSpark acceptance) - within noise of TP8xPP1 (100.8), ~2.3x faster than PP8; needle 6/6 + 512k 3/3, coding 5/5; prefill 128k c1 7,716 / c16 23,780; decode 128k c8 164, 512k c8 85.","occurred_at":"2026-09-12T06:22:00Z","config":{"serving":"TP1xPP6 (7,7,7,7,7,5), util 0.95-0.96, DSpark k=5, fp8_ds_mla","engine":"localhost/vllm-backport-v41:sm80 Schaka v0.13.0 kit (c1b0907b overlay)"},"benchmarks":[{"metric":"c1_decode_tok_s","value":96.9,"unit":"tok/s","context":"PP6 best-of-4 (107.6 with 93.8% DSpark acceptance)"},{"metric":"dspark_accept_pct","value":93.8,"unit":"%","context":"PP6 on predictable content"},{"metric":"prefill_tok_s","value":23780,"unit":"tok/s","context":"PP6 c16 @128k"}]}