ViperEkura 88f8dca2c2 perf: enlarge prefill KV tile to BC=32 for D<=128 ... - Kernel is latency-bound (25% occupancy), not compute/bandwidth-bound - BC=16 wasted a cp.async wait + barrier + loop overhead per tiny tile - Double KV tile to BC=32 for D<=128; D=256 stays 16 (64KB > 48KB smem cap) - Retune MIN_BLOCKS per head_dim (32->6, 64->4, 128->3, 256->2) - Result: ~6-8% faster on L20, 0.93-1.20x vs torch SDPA, correctness unchanged		2026-07-10 17:43:23 +08:00
..
kernels	perf: enlarge prefill KV tile to BC=32 for D<=128	2026-07-10 17:43:23 +08:00
tests	perf: enlarge prefill KV tile to BC=32 for D<=128	2026-07-10 17:43:23 +08:00
__init__.py	feat: add optional CUDA kernel system (csrc/) + fused GQA decode attention	2026-07-06 12:09:58 +08:00
build.py	perf: add fast-math and vectorization nvcc/cxx build flags	2026-07-07 22:28:32 +08:00