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>

pyproject.toml

@@ -29,13 +29,14 @@ openai = ["openai>=1.12"]
 anthropic = ["anthropic>=0.39"]
 local = ["litellm>=1.40"]
 api = ["fastapi>=0.115", "uvicorn>=0.32", "httpx>=0.27"]
+gpu = ["tensorflow>=2.16", "numpy>=1.26"]
 maa = []
 dev = [
     "pytest>=7.4",
     "mypy>=1.8",
     "ruff>=0.4",
 ]
-all = ["fusionagi[openai,anthropic,local]"]
+all = ["fusionagi[openai,anthropic,local,gpu]"]
 
 [project.urls]
 Repository = "https://github.com/fusionagi/fusionagi"