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

scripts/run_nsys_mega_moe_sm90.sh

@@ -0,0 +1,52 @@
+#!/bin/bash
+set -e
+
+NUM_RANKS=${NUM_RANKS:-2}
+NUM_TOKENS=${NUM_TOKENS:-128}
+HIDDEN=${HIDDEN:-4096}
+INTERMEDIATE=${INTERMEDIATE:-2048}
+NUM_EXPERTS=${NUM_EXPERTS:-16}
+NUM_TOPK=${NUM_TOPK:-6}
+OUTPUT_DIR=${OUTPUT_DIR:-./nsys-results}
+
+mkdir -p "$OUTPUT_DIR"
+
+TIMESTAMP=$(date +%Y%m%d_%H%M%S)
+REPORT_NAME="nsys_sm90_megamoe_t${NUM_TOKENS}_r${NUM_RANKS}_${TIMESTAMP}"
+
+echo "=== SM90 MegaMoE nsys profiling ==="
+echo "  Ranks: $NUM_RANKS"
+echo "  Tokens: $NUM_TOKENS"
+echo "  Hidden: $HIDDEN"
+echo "  Intermediate: $INTERMEDIATE"
+echo "  Experts: $NUM_EXPERTS"
+echo "  TopK: $NUM_TOPK"
+echo "  Output: $OUTPUT_DIR/$REPORT_NAME"
+echo ""
+
+NSYS_FLAGS=(
+    --trace=cuda,nvtx
+    --cuda-memory-usage=true
+    --force-overwrite=true
+    --output="$OUTPUT_DIR/$REPORT_NAME"
+    --stats=true
+)
+
+TORCH_FLAGS=(
+    --nproc_per_node="$NUM_RANKS"
+)
+
+TEST_FLAGS=(
+    --num-tokens="$NUM_TOKENS"
+    --hidden="$HIDDEN"
+    --intermediate-hidden="$INTERMEDIATE"
+    --num-experts="$NUM_EXPERTS"
+    --num-topk="$NUM_TOPK"
+)
+
+nsys profile "${NSYS_FLAGS[@]}" \
+    torchrun "${TORCH_FLAGS[@]}" \
+    tests/test_mega_moe_sm90.py "${TEST_FLAGS[@]}"
+
+echo ""
+echo "=== Done. Report: $OUTPUT_DIR/$REPORT_NAME.nsys-rep ==="