root
cdcf115037
feat: CUTLASS Cu10 grouped GEMM — real device verified
BI-V100 real device results:
moe_group_gemm: err=0.000015 PASS
moe_decode_cutlass: NaN=False PASS
cutlass grouped: 4.77ms vs torch.mm loop: 9.38ms → 1.97x speedup
Fix: gemm_grouped.cu ldb=K (not N) for ColumnMajor B view
Link: -lcuinfer from /usr/local/corex-3.2.3/lib64/libcuinfer.so.7
2026-08-17 04:18:29 +00:00
..
2026-08-12 01:33:24 +00:00
2026-08-15 14:15:47 +00:00
2026-08-12 01:33:24 +00:00
2026-08-12 01:33:24 +00:00
2026-08-12 01:33:24 +00:00
2026-08-10 02:31:55 +00:00
2026-08-15 14:15:47 +00:00
2026-08-17 04:18:29 +00:00
2026-08-13 02:48:28 +00:00
2026-08-12 01:33:24 +00:00
2026-08-15 14:15:47 +00:00
2026-08-15 06:15:17 +00:00
2026-08-17 02:16:58 +00:00
2026-08-10 03:10:58 +00:00
2026-08-10 02:55:58 +00:00
2026-08-17 02:16:58 +00:00
2026-08-15 14:13:13 +00:00
2026-08-15 06:15:17 +00:00
2026-08-15 14:13:13 +00:00