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
..
gqa_common.cuh	fix: correct prefill mask index, unify GQA kernel interface	2026-07-06 17:21:23 +08:00
gqa_decode_attn.cu	perf: add split-K (FlashDecoding) to decode MMA kernel	2026-07-10 11:43:18 +08:00
gqa_decode_attn.cuh	fix: correct prefill mask index, unify GQA kernel interface	2026-07-06 17:21:23 +08:00
gqa_decode_attn_mma.cuh	perf: add split-K (FlashDecoding) to decode MMA kernel	2026-07-10 11:43:18 +08:00
gqa_mma_utils.cuh	perf: pipeline prefill MMA kernel (double-buffered K/V + packed stores)	2026-07-10 12:19:14 +08:00
gqa_prefill_attn.cu	perf: enlarge prefill KV tile to BC=32 for D<=128	2026-07-10 17:43:23 +08:00
gqa_prefill_attn.cuh	perf: reduce MMA kernel registers, switch to static smem	2026-07-10 00:39:47 +08:00
gqa_prefill_attn_mma.cuh	perf: enlarge prefill KV tile to BC=32 for D<=128	2026-07-10 17:43:23 +08:00