{"model":"deepseek-4.1-flash","title":"PP6 sweep completed to the full 1M context","status":"positive","summary":"Prefix-cached decode aggregate: 4k 49/91/109/146/142 (c1/c2/c4/c8/c16), 32k 45/81/104/159/160, 128k 43/66/100/165/150, 512k 30/46/54/85/88, 1M 16/22 (only c1/c2 fit the 2.89M pool). DSpark acceptance rises to 51.7% @1M. Prefill: 1M c1 TTFT 342.5 s (~3.1k tok/s).","occurred_at":"2026-09-12T07:47:00Z","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":"agg_decode_32k_tok_s","value":159,"unit":"tok/s","context":"PP6 c8 @32k (160 @c16)"},{"metric":"agg_decode_512k_tok_s","value":85,"unit":"tok/s","context":"PP6 c8 @512k (88 @c16)"},{"metric":"agg_decode_1m_tok_s","value":16,"unit":"tok/s","context":"PP6 c1 @1M (22 @c2)"},{"metric":"prefill_tok_s","value":3100,"unit":"tok/s","context":"1M ctx c1 TTFT 342.5 s"}]}