DeepSeek V4 Flash 284B (13B active)

User reports DeepSeek V4 Flash at 1974.7 t/s prefill and 73.7 t/s decode at 510K input on a single L40S 48GB, up from 1147.2 t/s prefill and 26.1 t/s decode with the official engine's auto settings. Setup is a modified Strata v0.2.6 build with IQ1_M weights, CPU experts kept on NUMA0 of dual EPYC 9754 with about 1TB system RAM, 16384-token prefill chunks, a 384MiB reconstructed-weight cache, and DSpark/MTP speculative decoding at a 0.15 confidence threshold. Decode peaks at 76.9 t/s at 32K input; the official engine with DSpark forced on reached 1278.4 t/s prefill and 22.9 t/s decode at 510K.