Merge upstream ollama/ollama main branch while preserving CUDA 3.7 support

- Added support for new gpt-oss model from upstream
- Preserved CUDA Compute Capability 3.7 (Tesla K80) support
- Kept CUDA 11 configuration alongside CUDA 12
- Maintained all documentation specific to ollama37 fork
- Integrated new tool parsing improvements
- Added new backend methods and patches from upstream

.bmad-core/core-config.yaml

@@ -0,0 +1,20 @@
+markdownExploder: true
+prd:
+  prdFile: docs/prd.md
+  prdVersion: v4
+  prdSharded: true
+  prdShardedLocation: docs/prd
+  epicFilePattern: epic-{n}*.md
+architecture:
+  architectureFile: docs/architecture.md
+  architectureVersion: v4
+  architectureSharded: true
+  architectureShardedLocation: docs/architecture
+customTechnicalDocuments: null
+devLoadAlwaysFiles:
+  - docs/architecture/coding-standards.md
+  - docs/architecture/tech-stack.md
+  - docs/architecture/source-tree.md
+devDebugLog: .ai/debug-log.md
+devStoryLocation: docs/stories
+slashPrefix: BMad