Skip to content

v1.3.1 — fused short-prefill attention (TTFT win)

Latest

Choose a tag to compare

@ai-hpc ai-hpc released this 22 Jun 00:16
9de2130

The default cuBLAS prefill attention has per-call overhead (handle setup, ~70
batched-GEMM + softmax launches/layer, N×N score-buffer traffic) that dominates
at small sequence length. genie now dispatches the fused F32 query-tiled kernel
below a ~768-token crossover (cuBLAS's tensor-core GEMMs win at long context).

Prefill tok/s (cuBLAS-only → length-dispatch), Gemma 4 E2B on Orin

length before after Δ
~76 224 461 2.05×
~236 475 690 1.45×
~547 587 632 1.08×
~1547 640 639
~9098 537 537

Typical 50–300-token interactive prompts prefill ~1.4–2× faster (TTFT); long
context unchanged. vs llama.cpp real cold prompt-eval (llama-simple), genie
short-prefill is 2–7× faster (llama pays a ~1–2 s warmup genie does not).
JLLM_ATTN_SHORT_TILED=0 reverts.

Full Changelog: v1.3.0...v1.3.1