.dockerignore
.gitignore
ARCHITECTURE.md
CONFIGURATION.md
CONTRIBUTING.md
DASHBOARD_RPC_FIX.md
DISTRIBUTED_NODE_FIXES.md
DOCUMENTATION_UPDATES_2025-10-20.md
Dockerfile
EXPERIMENTAL_FEATURES.md
FINAL_LINT_FIX.md
INSTALLATION.md
INTELLIGENT_NODE_DISCOVERY.md
LICENSE
MANIFEST.in
QUICK_START.md
README.md
RPC_BACKEND_DISCOVERY_COMPLETE.md
RPC_ROUTING_FIX.md
SECURITY.md
SOLLOL_CONFIGURATION_GUIDE.md
SOLLOL_CONFIG_QUICK_REF.md
SOLLOL_DISCOVERY_PRIORITY_FIX.md
SOLLOL_LOCALITY_AWARENESS_ISSUE.md
SOLLOL_LOCK_OPTIMIZATION.md
TERMINOLOGY_CLARIFICATION.md
UNIFIED_OBSERVABILITY.md
compare_discovery_modes.py
config.yml
dashboard.html
demo_distributed_setup.sh
docker-compose.test.yml
docker-compose.yml
gpu_reporter.py
log_streamer.py
mkdocs.yml
prometheus.yml
pyproject.toml
rpc_backends.conf
setup.py
setup_llama_cpp.py
test_activity.py
test_batch_api.py
test_connection_reuse.py
test_dashboard.py
test_dashboard_command.py
test_dashboard_fallback_simple.py
test_dashboards.py
test_dask_adaptive.py
test_dask_batch.py
test_dask_comparison.py
test_docker.sh
test_embed_batch.py
test_failure_recovery.py
test_full_network_discovery.py
test_integration.py
test_locality_awareness.py
test_multi_app_dashboard.py
test_new_features.py
test_observer_debug.py
test_optimizations.py
test_ray_features.py
test_remote_coordinator.py
test_resilience.py
test_routing_log.py
test_routing_strategies.py
test_routing_validation.py
test_rpc_backend_fix.py
test_vram_monitoring.py
test_websocket_client.py
verify_dashboards.py
verify_parallel_nodes.py
.github/ISSUE_TEMPLATE/bug_report.md
.github/ISSUE_TEMPLATE/feature_request.md
.github/ISSUE_TEMPLATE/performance_issue.md
.github/workflows/docs.yml
.github/workflows/flake8-requirements.txt
.github/workflows/lint.yml
.github/workflows/publish.yml
.github/workflows/tests.yml
benchmarks/README.md
benchmarks/load_test.py
benchmarks/run_benchmarks.py
benchmarks/simple_ollama_benchmark.py
benchmarks/results/README.md
benchmarks/results/ollama_benchmark_llama3.2_1759757430.json
config/hosts.txt
docs/EXPERIMENTAL_FEATURES_SUMMARY.md
docs/GPU_DETECTION_SETUP.md
docs/HYBRID_RPC_PARALLELIZATION.md
docs/LIGHTWEIGHT_DISTRIBUTED_MODE.md
docs/MULTI_APP_OBSERVABILITY.md
docs/README.md
docs/index.md
docs/layer_partitioning.md
docs/llama_cpp_guide.md
docs/architecture/multi-app.md
docs/architecture/remote-coordinator.md
docs/archive/COMPLETE_SUMMARY.md
docs/archive/DEPLOYMENT.md
docs/archive/HONEST_STATUS.md
docs/archive/LEGACY_GPU_SUPPORT.md
docs/archive/PHASE1_IMPLEMENTATION_COMPLETE.md
docs/archive/PHASE2_COMPLETE.md
docs/archive/PHASE2_PROGRESS.md
docs/archive/PRODUCTION_READINESS.md
docs/archive/PUBLISH.md
docs/archive/PUBLISHING.md
docs/archive/PYPI_PUBLICATION_SUCCESS.md
docs/archive/REMOTE_ACCESS_STATUS.md
docs/archive/ROUTING_LOGS.md
docs/archive/SESSION_SUMMARY.md
docs/benchmarks/distributed-testing.md
docs/benchmarks/how-to-benchmark.md
docs/benchmarks/results.md
docs/benchmarks/test-results.md
docs/enterprise/roadmap.md
docs/external/FLOCKPARSER_FEATURES_ANALYSIS.md
docs/external/github-issues/llamacpp_github_issue.md
docs/external/github-issues/ollama_github_issue.md
docs/external/ollama-posts/ollama_discussion_discord_final.md
docs/external/ollama-posts/ollama_discussion_draft.md
docs/external/ollama-posts/ollama_discussion_draft_v2.md
docs/external/ollama-posts/ollama_discussion_final.md
docs/external/ollama-posts/ollama_discussion_followup.md
docs/features/backends.md
docs/features/batch-processing.md
docs/features/dashboard.md
docs/features/deployment-aware-resolution.md
docs/features/docker-networking.md
docs/features/routing.md
docs/getting-started/quick-start.md
docs/integration/advanced.md
docs/integration/basic.md
docs/integration/code-walkthrough.md
docs/screenshots/dashboard-activity.png
docs/screenshots/dashboard-metrics.png
docs/screenshots/dashboard-overview.png
docs/screenshots/dashboard-ray-dask.png
docs/setup/deploy-gpu-reporter.md
docs/setup/docker.md
docs/setup/gpu-monitoring-guide.md
docs/setup/gpu-monitoring-setup.md
docs/setup/grafana.md
docs/setup/ray-cluster.md
docs/setup/redis.md
docs/setup/remote-access.md
docs/troubleshooting/coordinator-investigation.md
docs/troubleshooting/known-issues.md
docs/troubleshooting/limitations.md
docs/troubleshooting/rpc-fixes.md
examples/adaptive_parallelism_example.py
examples/application_integration.py
examples/auto_setup_example.py
examples/basic_usage.py
examples/cluster_example.py
examples/dashboard_application_tracking.py
examples/live_dashboard_demo.py
examples/llama_cpp_distributed.py
examples/multi_machine_setup.py
examples/quick_start.py
examples/ray_advanced_features.py
examples/ray_hybrid_router_usage.py
examples/ray_vs_basic_hybrid_router.py
examples/unified_dashboard_demo.py
examples/integration/README.md
examples/integration/load_balancer_wrapper.py
examples/integration/priority_mapping.py
examples/integration/sync_agents.py
kubernetes/README.md
kubernetes/ollama-nodes.yaml
kubernetes/sollol-gateway.yaml
scripts/README.md
scripts/check_gpu_status.sh
scripts/configure_redis_network.sh
scripts/deploy_to_cluster.sh
scripts/install-all-services.sh
scripts/install-gpu-reporter-service.sh
scripts/install-rpc-service.sh
scripts/install_cuda_llama.sh
scripts/register_gpu_node.py
scripts/setup_rpc_node.py
src/sollol/__init__.py
src/sollol/adapters.py
src/sollol/adaptive_metrics.py
src/sollol/adaptive_parallelism.py
src/sollol/aggregation.py
src/sollol/auth.py
src/sollol/autobatch.py
src/sollol/batch.py
src/sollol/batch_manager.py
src/sollol/circuit_breaker.py
src/sollol/cli.py
src/sollol/client.py
src/sollol/cluster.py
src/sollol/config.py
src/sollol/coordinator_manager.py
src/sollol/dashboard.py
src/sollol/dashboard_client.py
src/sollol/dashboard_launcher.py
src/sollol/dashboard_log_hooks.py
src/sollol/dashboard_service.py
src/sollol/discovery.py
src/sollol/distributed_coordinator.py
src/sollol/distributed_pipeline.py
src/sollol/distributed_tracing.py
src/sollol/docker_ip_resolver.py
src/sollol/embedding_cache.py
src/sollol/execution.py
src/sollol/gateway.py
src/sollol/gpu_auto_setup.py
src/sollol/gpu_controller.py
src/sollol/gpu_redis_subscriber.py
src/sollol/graceful_shutdown.py
src/sollol/hedging.py
src/sollol/hedging_async.py
src/sollol/hybrid_router.py
src/sollol/install_systemd_service.py
src/sollol/integration.py
src/sollol/intelligence.py
src/sollol/intelligent_gpu_router.py
src/sollol/llama_cpp_coordinator.py
src/sollol/llama_cpp_rpc.py
src/sollol/memory.py
src/sollol/metrics.py
src/sollol/metrics_logger.py
src/sollol/model_sizes.py
src/sollol/network_observer.py
src/sollol/node_cluster.py
src/sollol/node_health.py
src/sollol/ollama_gguf_resolver.py
src/sollol/ollama_node.py
src/sollol/pool.py
src/sollol/prioritization.py
src/sollol/priority_helpers.py
src/sollol/rate_limiter.py
src/sollol/ray_advanced_router.py
src/sollol/ray_hybrid_router.py
src/sollol/registry.py
src/sollol/request_timeout.py
src/sollol/response_cache.py
src/sollol/retry_logic.py
src/sollol/routing_logger.py
src/sollol/routing_strategy.py
src/sollol/routing_viewer.py
src/sollol/rpc_auto_setup.py
src/sollol/rpc_discovery.py
src/sollol/rpc_registry.py
src/sollol/serve.py
src/sollol/setup_llama_cpp.py
src/sollol/sollol.py
src/sollol/sync_wrapper.py
src/sollol/tasks.py
src/sollol/unified_dashboard.py
src/sollol/vram_monitor.py
src/sollol/workers.py
src/sollol.egg-info/PKG-INFO
src/sollol.egg-info/SOURCES.txt
src/sollol.egg-info/dependency_links.txt
src/sollol.egg-info/entry_points.txt
src/sollol.egg-info/not-zip-safe
src/sollol.egg-info/requires.txt
src/sollol.egg-info/top_level.txt
systemd/sollol-gpu-reporter.service
systemd/sollol-rpc-server.service
tests/__init__.py
tests/conftest.py
tests/test_docker_ip_resolver.py
tests/integration/__init__.py
tests/integration/mock_ollama_server.py
tests/integration/test_dashboard_rpc_backends.py
tests/integration/test_fault_tolerance.py
tests/integration/test_multi_node_routing.py
tests/unit/__init__.py
tests/unit/test_intelligence.py
tests/unit/test_prioritization.py
tests/unit/test_rpc_backend_metadata.py