biondizzle/nvfp4-megamoe-kernel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
512 Commits 1 Branch 17 Tags
50e9b5da81477e000e4770e94de9d175204f5ff0
Commit Graph

1 Commits

Author SHA1 Message Date
biondizzle
6ce6a47be9 Add NVFP4 linear runner + attention projection test 
- CuTeDSLNvfp4Linear: generic single-GEMM runner for any NVFP4 projection
- test_attention.py: tests q_a_proj, q_b_proj, kv_proj, o_b_proj vs BF16
- Same pad+swizzle pattern as shared expert, but no SiLU/fusion
 2026-05-18 20:14:03 +00:00