feat: GPU/TensorCore integration — TensorFlow backend, GPU-accelerated reasoning, training, and memory

- New fusionagi/gpu/ module with TensorBackend protocol abstraction
  - TensorFlowBackend: GPU-accelerated ops with TensorCore mixed-precision
  - NumPyBackend: CPU fallback (always available, no extra deps)
  - Auto-selects best available backend at runtime

- GPU-accelerated operations:
  - Cosine similarity matrix (batched, XLA-compiled)
  - Multi-head attention for consensus scoring
  - Batch hypothesis scoring on GPU
  - Semantic similarity search (pairwise, nearest-neighbor, deduplication)

- New TensorFlowAdapter (fusionagi/adapters/):
  - LLMAdapter for local TF/Keras model inference
  - TensorCore mixed-precision support
  - GPU-accelerated embedding synthesis fallback

- Reasoning pipeline integration:
  - gpu_scoring.py: drop-in GPU replacement for multi_path scoring
  - Super Big Brain: use_gpu config flag, GPU scoring when available

- Memory integration:
  - gpu_search.py: GPU-accelerated semantic search for SemanticGraphMemory

- Self-improvement integration:
  - gpu_training.py: gradient-based heuristic weight optimization
  - Reflective memory training loop with loss tracking

- Dependencies: gpu extra (tensorflow>=2.16, numpy>=1.26)
- 64 new tests (276 total), all passing
- Architecture spec: docs/gpu_tensorcore_integration.md

Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>

fusionagi/core/super_big_brain.py

@@ -12,6 +12,7 @@ from fusionagi.reasoning.decomposition import decompose_recursive
 from fusionagi.reasoning.context_loader import load_context_for_reasoning, build_compact_prompt
 from fusionagi.reasoning.tot import ThoughtNode, expand_node, prune_subtree, merge_subtrees
 from fusionagi.reasoning.multi_path import generate_and_score_parallel
+from fusionagi.reasoning.gpu_scoring import generate_and_score_gpu
 from fusionagi.reasoning.recomposition import recompose, RecomposedResponse
 from fusionagi.reasoning.meta_reasoning import challenge_assumptions, detect_contradictions
 from fusionagi.memory.semantic_graph import SemanticGraphMemory
@@ -30,6 +31,7 @@ class SuperBigBrainConfig:
     parallel_hypotheses: int = 3
     prune_threshold: float = 0.3
     max_context_chars: int = 4000
+    use_gpu: bool = True
 
 
 def run_super_big_brain(
@@ -60,7 +62,10 @@ def run_super_big_brain(
     if not hypotheses:
         hypotheses = [compact[:500]]
 
-    scored = generate_and_score_parallel(hypotheses, decomp.units)
+    if cfg.use_gpu:
+        scored = generate_and_score_gpu(hypotheses, decomp.units)
+    else:
+        scored = generate_and_score_parallel(hypotheses, decomp.units)
     nodes = [n for n, _ in sorted(scored, key=lambda x: x[1], reverse=True)]
     best = nodes[0] if nodes else ThoughtNode(thought=compact[:300], unit_refs=[u.unit_id for u in decomp.units[:5]])