This website requires JavaScript.
Explore
Help
Register
Sign In
biondizzle
/
nvfp4-megamoe-kernel
Watch
1
Star
0
Fork
0
You've already forked nvfp4-megamoe-kernel
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
Wiki
Activity
Files
ef4c0ad4893181ec6d76a9ecc8d7d5b8fd03f94d
nvfp4-megamoe-kernel
/
dsv4
/
kernels
/
router
History
biondizzle
ef4c0ad489
Fix BF16 router mma_tiler: use cutlass.Int32 for CuTe DSL compatibility
2026-06-01 07:29:30 +00:00
..
__init__.py
feat: NVFP4 gate projection for router (replaces BF16 cuBLAS)
2026-06-01 05:58:56 +00:00
_activation_topk.py
Router: full kernel stack — hash, topk, activation+topk, dense decode/prefill
2026-05-21 21:54:05 +00:00
dense_router_decode_kernel.py
Fix BF16 router mma_tiler: use cutlass.Int32 for CuTe DSL compatibility
2026-06-01 07:29:30 +00:00
dense_router_decode.py
feat: NVFP4 gate projection for router (replaces BF16 cuBLAS)
2026-06-01 05:58:56 +00:00
dense_router_prefill.py
Router: clean up dense_router_decode.py — realistic architecture, no fake code
2026-05-21 21:58:31 +00:00
nvfp4_fused_router_kernel.py
Fix: hardcode mma_inst_shape_k=32 for NVFP4 (avoids MLIR unpack error in JIT)
2026-06-01 07:20:23 +00:00