Xinyi Liu 062cb160cf Phase 0: SM90 MegaMoE design doc, reference baseline, nsys script ...

- MEGAMOE_SM90_DESIGN.md: complete design document with finalized decisions
  (fused single kernel, cooperative + single-WG, dynamic BLOCK_M, etc.)
- tests/test_mega_moe_sm90.py: PyTorch FP32/BF16 reference implementation
  for dispatch → L1 GEMM → SwiGLU → L2 GEMM → combine pipeline
- scripts/run_nsys_mega_moe_sm90.sh: nsys profiling wrapper script
- megamoe-research-reports/: research analysis of PR304/323/347/352/357/360

2026-06-16 18:01:12 +08:00

..

megamoe_sm90_research_report.md

Phase 0: SM90 MegaMoE design doc, reference baseline, nsys script

2026-06-16 18:01:12 +08:00

megamoe.jpg

Phase 0: SM90 MegaMoE design doc, reference baseline, nsys script

2026-06-16 18:01:12 +08:00

pr304_sm100_kernel_suite_code_review.md

Phase 0: SM90 MegaMoE design doc, reference baseline, nsys script

2026-06-16 18:01:12 +08:00

pr323_sm90_fused_megamoe_code_review.md

Phase 0: SM90 MegaMoE design doc, reference baseline, nsys script

2026-06-16 18:01:12 +08:00

pr347_infra_refactor_code_review.md

Phase 0: SM90 MegaMoE design doc, reference baseline, nsys script

2026-06-16 18:01:12 +08:00

pr352_sm90_split_l1l2_megamoe_code_review.md

Phase 0: SM90 MegaMoE design doc, reference baseline, nsys script

2026-06-16 18:01:12 +08:00

pr357_green_context_split_megamoe_notes.md

Phase 0: SM90 MegaMoE design doc, reference baseline, nsys script

2026-06-16 18:01:12 +08:00

pr360_sm90_pingpong_coop_megamoe_code_review.md

Phase 0: SM90 MegaMoE design doc, reference baseline, nsys script

2026-06-16 18:01:12 +08:00