README.md
pyproject.toml
async_scheduler/__init__.py
async_scheduler/async_runtime_engine.py
async_scheduler/cuda_stream_manager.py
async_scheduler/pipeline_coordinator.py
async_scheduler/prefetch_manager.py
async_scheduler/scheduler_config.py
async_scheduler/scheduler_metrics.py
async_scheduler/task_queue.py
async_scheduler/worker_pool.py
cli/__init__.py
cli/budget_cli.py
cli/health_cli.py
cli/knowledge_cli.py
cli/kv_cli.py
cli/learning_cli.py
cli/main.py
cli/optimizer_cli.py
cli/performance_cli.py
cli/commands/__init__.py
cli/commands/benchmark.py
cli/commands/cache_cmd.py
cli/commands/chat.py
cli/commands/config_cmd.py
cli/commands/doctor.py
cli/commands/hardware.py
cli/commands/inspect_cmd.py
cli/commands/logs_cmd.py
cli/commands/models_cmd.py
cli/commands/monitor_cmd.py
cli/commands/optimize.py
cli/commands/placement_cmd.py
cli/commands/plugins_cmd.py
cli/commands/profile.py
cli/commands/reset_cmd.py
cli/commands/run.py
cli/commands/serve.py
cli/commands/stats_cmd.py
cli/commands/telemetry_cmd.py
cli/commands/update_cmd.py
cli/commands/version_cmd.py
cli/core/__init__.py
cli/core/config_manager.py
cli/core/model_registry.py
cli/core/plugin_manager.py
cli/core/profile_manager.py
cli/core/telemetry_store.py
cli/tui/__init__.py
cli/tui/chat_ui.py
cli/tui/live_status.py
cli/tui/monitor_ui.py
cli/tui/settings_menu.py
cli/tui/telemetry_ui.py
cli/tui/themes.py
igpu_support/__init__.py
igpu_support/contention_model.py
igpu_support/igpu_profiler.py
igpu_support/placement_contributor.py
igpu_support/suitability_evaluator.py
igpu_support/workload_classifier.py
inference_runtime/__init__.py
inference_runtime/argument_builder.py
inference_runtime/backend_selector.py
inference_runtime/inference_session.py
inference_runtime/process_manager.py
inference_runtime/runtime_config.py
inference_runtime/runtime_engine.py
inference_runtime/stats_collector.py
inferenceos/__init__.py
inferenceos/__main__.py
inferenceos.egg-info/PKG-INFO
inferenceos.egg-info/SOURCES.txt
inferenceos.egg-info/dependency_links.txt
inferenceos.egg-info/entry_points.txt
inferenceos.egg-info/requires.txt
inferenceos.egg-info/top_level.txt
kv_manager/__init__.py
kv_manager/compression.py
kv_manager/eviction.py
kv_manager/importance.py
kv_manager/interfaces.py
kv_manager/manager.py
kv_manager/policy.py
kv_manager/quantization.py
kv_manager/statistics.py
kv_manager/telemetry.py
layer_migration/__init__.py
layer_migration/hysteresis_controller.py
layer_migration/memory_monitor.py
layer_migration/migration_config.py
layer_migration/migration_coordinator.py
layer_migration/migration_engine.py
layer_migration/migration_event.py
layer_migration/plan_mutator.py
layer_placement/__init__.py
layer_placement/cost_model.py
layer_placement/model_descriptor.py
layer_placement/optimizer.py
layer_placement/placement_engine.py
layer_placement/placement_plan.py
layer_placement/report_generator.py
memory_budget/__init__.py
memory_budget/allocator.py
memory_budget/budgets.py
memory_budget/interfaces.py
memory_budget/manager.py
memory_budget/planner.py
memory_budget/policies.py
memory_manager/__init__.py
memory_manager/accounting.py
memory_manager/memory_tier.py
memory_manager/tensor.py
memory_manager/unified_memory_manager.py
optimizer/__init__.py
optimizer/confidence.py
optimizer/engine.py
optimizer/fingerprint.py
optimizer/history.py
optimizer/interfaces.py
optimizer/profiles.py
optimizer/search.py
optimizer/storage.py
optimizer/validation.py
orchestrator/__init__.py
orchestrator/backend_wrapper.py
orchestrator/engine.py
orchestrator/gguf_parser.py
orchestrator/gguf_selector.py
orchestrator/memory_planner.py
performance_intelligence/__init__.py
performance_intelligence/analysis.py
performance_intelligence/baseline.py
performance_intelligence/engine.py
performance_intelligence/events.py
performance_intelligence/interfaces.py
performance_intelligence/recommendation.py
performance_intelligence/regression.py
performance_intelligence/statistics.py
performance_intelligence/storage.py
performance_intelligence/trend.py
profiler/__init__.py
profiler/cpu_profiler.py
profiler/gpu_profiler.py
profiler/hardware_profiler.py
profiler/interconnect_profiler.py
profiler/memory_profiler.py
profiler/resource_model.py
profiler/storage_profiler.py
profiler/gpu_backends/__init__.py
profiler/gpu_backends/amd_backend.py
profiler/gpu_backends/apple_backend.py
profiler/gpu_backends/intel_backend.py
profiler/gpu_backends/nvidia_backend.py
runtime_health/__init__.py
runtime_health/alerts.py
runtime_health/events.py
runtime_health/metrics.py
runtime_health/monitor.py
runtime_health/sensors.py
runtime_health/statistics.py
runtime_kb/__init__.py
runtime_kb/backend.py
runtime_kb/database.py
runtime_kb/hardware.py
runtime_kb/interfaces.py
runtime_kb/knowledge_base.py
runtime_kb/models.py
runtime_kb/performance.py
runtime_kb/query.py
runtime_kb/recommendation.py
runtime_kb/scheduler.py
runtime_kb/statistics.py
runtime_kb/storage.py
runtime_learning/__init__.py
runtime_learning/confidence.py
runtime_learning/database.py
runtime_learning/engine.py
runtime_learning/history.py
runtime_learning/knowledge.py
runtime_learning/prediction.py
runtime_learning/recommendation.py
runtime_learning/statistics.py
runtime_memory/__init__.py
runtime_memory/buffer_planner.py
runtime_memory/kv_estimator.py
runtime_memory/memory_budget.py
runtime_memory/preflight_guard.py
runtime_memory/risk_classifier.py
runtime_memory/warning_generator.py
runtime_profiler/__init__.py
runtime_profiler/flame_graph.py
runtime_profiler/optimization_advisor.py
runtime_profiler/performance_report.py
runtime_profiler/profiler_engine.py
runtime_profiler/telemetry_collector.py
runtime_profiler/timeline_view.py
scheduler/__init__.py
scheduler/config.py
scheduler/context_config.py
scheduler/context_decision.py
scheduler/context_heuristics.py
scheduler/context_scheduler.py
scheduler/decision.py
scheduler/feedback_store.py
scheduler/heuristics.py
scheduler/memory_config.py
scheduler/memory_decision.py
scheduler/memory_policies.py
scheduler/memory_scheduler.py
scheduler/microbatch_scheduler.py
server/__init__.py
server/config.py
server/server_runner.py
server/api/__init__.py
server/api/app.py
server/api/routes/__init__.py
server/api/routes/chat.py
server/api/routes/completions.py
server/api/routes/embeddings.py
server/api/routes/health.py
server/api/routes/metrics.py
server/api/routes/models.py
server/api/routes/ollama.py
server/api/routes/responses.py
server/api/routes/sessions.py
server/metrics/__init__.py
server/metrics/telemetry.py
server/middleware/__init__.py
server/middleware/auth.py
server/middleware/error_handler.py
server/middleware/logging.py
server/models/__init__.py
server/models/openai.py
server/models/session_models.py
server/queue/__init__.py
server/queue/request_queue.py
server/runtime_adapter/__init__.py
server/runtime_adapter/adapter.py
server/sessions/__init__.py
server/sessions/session.py
server/sessions/session_manager.py
server/streaming/__init__.py
server/streaming/sse.py
setup/__init__.py
setup/build_engine.py
setup/build_validator.py
setup/cmake_profiles.py
setup/prerequisites.py
tests/test_async_scheduler.py
tests/test_backend_wrapper.py
tests/test_build_engine.py
tests/test_context_scheduler.py
tests/test_gguf_parser.py
tests/test_gguf_selector.py
tests/test_igpu_support.py
tests/test_inference_runtime.py
tests/test_kv_manager.py
tests/test_layer_migration.py
tests/test_layer_placement.py
tests/test_memory_budget.py
tests/test_memory_manager.py
tests/test_memory_planner.py
tests/test_memory_scheduler.py
tests/test_microbatch_scheduler.py
tests/test_openai_server.py
tests/test_optimizer.py
tests/test_performance_intelligence.py
tests/test_profiler.py
tests/test_runtime_health.py
tests/test_runtime_kb.py
tests/test_runtime_learning.py
tests/test_runtime_memory.py
tests/test_runtime_profiler.py
tests/test_server.py