LICENSE
README.md
pyproject.toml
src/distllm/__init__.py
src/distllm/constants.py
src/distllm/py.typed
src/distllm/api/__init__.py
src/distllm/api/api_settings.py
src/distllm/api/api_state.py
src/distllm/api/api_versioning.py
src/distllm/api/app_state.py
src/distllm/api/auth_deps.py
src/distllm/api/background_tasks.py
src/distllm/api/body_cache_middleware.py
src/distllm/api/circuit_breaker_middleware.py
src/distllm/api/cost_middleware.py
src/distllm/api/csrf_middleware.py
src/distllm/api/dedup.py
src/distllm/api/errors.py
src/distllm/api/grpc_bridge.py
src/distllm/api/ip_utils.py
src/distllm/api/middleware.py
src/distllm/api/observability_middleware.py
src/distllm/api/persistent_store.py
src/distllm/api/prompt_injection.py
src/distllm/api/quota_middleware.py
src/distllm/api/rate_limit_middleware.py
src/distllm/api/rate_limiter.py
src/distllm/api/rate_limiter_unified.py
src/distllm/api/redis_rate_limiter.py
src/distllm/api/semantic_cache.py
src/distllm/api/server.py
src/distllm/api/server_config.py
src/distllm/api/server_coordinator.py
src/distllm/api/server_errors.py
src/distllm/api/server_lifespan.py
src/distllm/api/server_routes_api.py
src/distllm/api/server_routes_dashboard.py
src/distllm/api/server_state.py
src/distllm/api/sso_auth.py
src/distllm/api/sso_middleware.py
src/distllm/api/streaming.py
src/distllm/api/token_estimator.py
src/distllm/api/tool_calling.py
src/distllm/api/tracing_middleware.py
src/distllm/api/validation.py
src/distllm/api/waf.py
src/distllm/api/ws_chat.py
src/distllm/api/auth/__init__.py
src/distllm/api/auth/models.py
src/distllm/api/auth/oauth2.py
src/distllm/api/auth/oidc.py
src/distllm/api/auth/saml.py
src/distllm/api/auth/store.py
src/distllm/api/authz/__init__.py
src/distllm/api/authz/opa.py
src/distllm/api/routes/__init__.py
src/distllm/api/routes/admin.py
src/distllm/api/routes/api_keys.py
src/distllm/api/routes/assistants.py
src/distllm/api/routes/batch.py
src/distllm/api/routes/chat.py
src/distllm/api/routes/completion.py
src/distllm/api/routes/debug.py
src/distllm/api/routes/defrag.py
src/distllm/api/routes/embeddings.py
src/distllm/api/routes/eval.py
src/distllm/api/routes/exchange.py
src/distllm/api/routes/experiments.py
src/distllm/api/routes/federated.py
src/distllm/api/routes/files.py
src/distllm/api/routes/fine_tuning.py
src/distllm/api/routes/gossip.py
src/distllm/api/routes/health.py
src/distllm/api/routes/leaderboard.py
src/distllm/api/routes/marketplace.py
src/distllm/api/routes/metrics_history.py
src/distllm/api/routes/model_registry.py
src/distllm/api/routes/moderation.py
src/distllm/api/routes/plugins.py
src/distllm/api/routes/prompts.py
src/distllm/api/routes/router_admin.py
src/distllm/api/routes/scheduler.py
src/distllm/api/routes/tokenize.py
src/distllm/api/routes/tools.py
src/distllm/api/routes/webhooks.py
src/distllm/api/routes/webrtc.py
src/distllm/api/services/__init__.py
src/distllm/api/services/chat_service.py
src/distllm/api/services/completion_service.py
src/distllm/api/services/embedding_service.py
src/distllm/api/services/eval_service.py
src/distllm/api/webhooks/__init__.py
src/distllm/api/webhooks/delivery.py
src/distllm/backends/__init__.py
src/distllm/backends/config.py
src/distllm/backends/exllama_backend.py
src/distllm/backends/llamacpp_backend.py
src/distllm/backends/mlx_backend.py
src/distllm/backends/nim_backend.py
src/distllm/backends/ollama_backend.py
src/distllm/backends/onnx_backend.py
src/distllm/backends/paged_attention.py
src/distllm/backends/paged_attention_quantized.py
src/distllm/backends/protocol.py
src/distllm/backends/pytorch_backend.py
src/distllm/backends/registry.py
src/distllm/backends/tensorrt_backend.py
src/distllm/backends/tgi_backend.py
src/distllm/backends/triton_backend.py
src/distllm/backends/vllm_backend.py
src/distllm/backends/webgpu_backend.py
src/distllm/benchmarks/__init__.py
src/distllm/benchmarks/evaluation_harness.py
src/distllm/benchmarks/scaling.py
src/distllm/cache/__init__.py
src/distllm/cache/crdt.py
src/distllm/cache/cross_cluster_prefix_index.py
src/distllm/cli/__init__.py
src/distllm/cli/adapters.py
src/distllm/cli/autopsy.py
src/distllm/cli/backup.py
src/distllm/cli/benchmark.py
src/distllm/cli/cert.py
src/distllm/cli/chat.py
src/distllm/cli/chat_stream.py
src/distllm/cli/client.py
src/distllm/cli/cluster.py
src/distllm/cli/completion.py
src/distllm/cli/compress.py
src/distllm/cli/config_commands.py
src/distllm/cli/cost_avoid.py
src/distllm/cli/daas_commands.py
src/distllm/cli/defrag_commands.py
src/distllm/cli/deploy.py
src/distllm/cli/doctor.py
src/distllm/cli/draft_commands.py
src/distllm/cli/error_handler.py
src/distllm/cli/eval.py
src/distllm/cli/federate_commands.py
src/distllm/cli/install.py
src/distllm/cli/logs.py
src/distllm/cli/main.py
src/distllm/cli/models.py
src/distllm/cli/notify.py
src/distllm/cli/observe.py
src/distllm/cli/onboard.py
src/distllm/cli/output.py
src/distllm/cli/profile.py
src/distllm/cli/profile_presets.py
src/distllm/cli/prompts.py
src/distllm/cli/quota.py
src/distllm/cli/router.py
src/distllm/cli/run.py
src/distllm/cli/setup.py
src/distllm/cli/setup_wizard.py
src/distllm/cli/status.py
src/distllm/cli/system_commands.py
src/distllm/cli/tune.py
src/distllm/cli/tutorial.py
src/distllm/cli/verify.py
src/distllm/cli/webhook.py
src/distllm/client/__init__.py
src/distllm/client/client.py
src/distllm/cloud/__init__.py
src/distllm/cloud/aws.py
src/distllm/cloud/azure.py
src/distllm/cloud/common.py
src/distllm/cloud/gcp.py
src/distllm/cloud/spot_orchestrator.py
src/distllm/cloud/worker_agent.py
src/distllm/compliance/__init__.py
src/distllm/compliance/evidence_pack.py
src/distllm/config/__init__.py
src/distllm/config/_application.py
src/distllm/config/_backends.py
src/distllm/config/_cache.py
src/distllm/config/_deployment.py
src/distllm/config/_generation.py
src/distllm/config/_hardware.py
src/distllm/config/_model.py
src/distllm/config/_network.py
src/distllm/config/_observability.py
src/distllm/config/_parallelism.py
src/distllm/config/_performance.py
src/distllm/config/loader.py
src/distllm/config/model_heuristics.py
src/distllm/config/profiles.py
src/distllm/config/reference.py
src/distllm/config/resolver.py
src/distllm/config/settings.py
src/distllm/core/__init__.py
src/distllm/core/ab_test_coordinator.py
src/distllm/core/activation_profiler.py
src/distllm/core/adaptive_batching.py
src/distllm/core/adaptive_cache_compressor.py
src/distllm/core/adaptive_compression.py
src/distllm/core/adaptive_compression_hierarchy.py
src/distllm/core/aegis_compliance.py
src/distllm/core/aether_federated.py
src/distllm/core/agentic_router.py
src/distllm/core/api_key_store.py
src/distllm/core/arbitrage_engine.py
src/distllm/core/aria_autoscaler.py
src/distllm/core/async_connection_pool.py
src/distllm/core/async_pipelined_speculative.py
src/distllm/core/atlas_mesh.py
src/distllm/core/auto_discovery.py
src/distllm/core/auto_partitioner.py
src/distllm/core/autonomous_healer.py
src/distllm/core/autoq.py
src/distllm/core/backup_manager.py
src/distllm/core/bargaining_engine.py
src/distllm/core/batch_builder.py
src/distllm/core/batch_scheduler.py
src/distllm/core/block_affinity_tracker.py
src/distllm/core/block_eviction_policy.py
src/distllm/core/cache_aware_router.py
src/distllm/core/cache_bench.py
src/distllm/core/cache_coherence.py
src/distllm/core/cache_doctor.py
src/distllm/core/cache_eviction.py
src/distllm/core/cache_index.py
src/distllm/core/cache_manager.py
src/distllm/core/cache_migration.py
src/distllm/core/cache_persistence.py
src/distllm/core/cache_query_log.py
src/distllm/core/cache_snapshot.py
src/distllm/core/cache_template_warmer.py
src/distllm/core/cache_warming.py
src/distllm/core/calibration.py
src/distllm/core/carbon_migration.py
src/distllm/core/cert_rotation.py
src/distllm/core/certificate_manager.py
src/distllm/core/cluster_manager.py
src/distllm/core/cluster_predictive_prefetcher.py
src/distllm/core/cluster_registry.py
src/distllm/core/cluster_state_store.py
src/distllm/core/compliance_evidence.py
src/distllm/core/compressed_speculative.py
src/distllm/core/connection_pool.py
src/distllm/core/constrained_decoder.py
src/distllm/core/coordinator.py
src/distllm/core/coordinator_cli.py
src/distllm/core/coordinator_config.py
src/distllm/core/coordinator_config_wiring.py
src/distllm/core/coordinator_election.py
src/distllm/core/coordinator_failover.py
src/distllm/core/coordinator_health.py
src/distllm/core/coordinator_lifecycle.py
src/distllm/core/coordinator_metrics.py
src/distllm/core/coordinator_multi_model.py
src/distllm/core/coordinator_request.py
src/distllm/core/coordinator_state.py
src/distllm/core/coordinator_subsystem.py
src/distllm/core/correctness_cert.py
src/distllm/core/correctness_harness.py
src/distllm/core/cortex_multimodel.py
src/distllm/core/cost_comparison.py
src/distllm/core/cost_dashboard.py
src/distllm/core/cost_optimizer.py
src/distllm/core/cost_tracker.py
src/distllm/core/cross_cloud_router.py
src/distllm/core/cross_model_prefix_sharing.py
src/distllm/core/cuda_graph.py
src/distllm/core/debug.py
src/distllm/core/device_registry.py
src/distllm/core/di.py
src/distllm/core/differential_privacy.py
src/distllm/core/distributed_distillation.py
src/distllm/core/distributed_speculative.py
src/distllm/core/dp_inference.py
src/distllm/core/draft_model_router.py
src/distllm/core/draft_quality_scorer.py
src/distllm/core/draft_tree.py
src/distllm/core/dynamic_memory_budget.py
src/distllm/core/dynamic_sharder.py
src/distllm/core/dynamic_speculation.py
src/distllm/core/evaluation_harness.py
src/distllm/core/event_bus.py
src/distllm/core/faas_7b.py
src/distllm/core/feature_flags.py
src/distllm/core/federated_finetuner.py
src/distllm/core/federated_incentives.py
src/distllm/core/framework_adapters.py
src/distllm/core/gaia_cache.py
src/distllm/core/gossip_cache_bridge.py
src/distllm/core/gpu_power_manager.py
src/distllm/core/gpu_profiler.py
src/distllm/core/gpu_resource_manager.py
src/distllm/core/graceful_degradation.py
src/distllm/core/grammar_constrained.py
src/distllm/core/grammar_constrained_draft.py
src/distllm/core/grammar_decoder.py
src/distllm/core/ha_coordinator.py
src/distllm/core/hardware_plugin_registry.py
src/distllm/core/hashing.py
src/distllm/core/health_manager.py
src/distllm/core/heterogeneous_scheduler.py
src/distllm/core/hibernation_manager.py
src/distllm/core/hierarchical_digest.py
src/distllm/core/hybrid_cache.py
src/distllm/core/hydra_diffusion.py
src/distllm/core/inference_engine.py
src/distllm/core/intelligent_autoscaler.py
src/distllm/core/kraken_chaos.py
src/distllm/core/kv_backup.py
src/distllm/core/kv_cache.py
src/distllm/core/kv_cache_adaptive_quantizer.py
src/distllm/core/kv_cache_compressor.py
src/distllm/core/kv_cache_manager.py
src/distllm/core/kv_cache_marketplace.py
src/distllm/core/kv_cache_metrics.py
src/distllm/core/kv_cache_migration.py
src/distllm/core/kv_cache_paged.py
src/distllm/core/kv_cache_replication.py
src/distllm/core/kv_cache_serialization.py
src/distllm/core/latency_tracker.py
src/distllm/core/leaky_bucket_limiter.py
src/distllm/core/learning_router.py
src/distllm/core/llamacpp_backend.py
src/distllm/core/load_balancer.py
src/distllm/core/media_pipeline.py
src/distllm/core/memory_defragmenter.py
src/distllm/core/metering.py
src/distllm/core/metrics_collector.py
src/distllm/core/micro_batch_scheduler.py
src/distllm/core/model_hub_enhanced.py
src/distllm/core/model_registry.py
src/distllm/core/model_router.py
src/distllm/core/model_selector.py
src/distllm/core/model_sizing.py
src/distllm/core/model_version_manager.py
src/distllm/core/moe_orchestrator.py
src/distllm/core/money.py
src/distllm/core/monitor.py
src/distllm/core/mtp_head.py
src/distllm/core/multi_draft_verifier.py
src/distllm/core/multi_model_serving.py
src/distllm/core/multimodal_engine.py
src/distllm/core/neural_partition_optimizer.py
src/distllm/core/node_recovery.py
src/distllm/core/notification_manager.py
src/distllm/core/param_update_channel.py
src/distllm/core/pareto_optimizer.py
src/distllm/core/performance_alerts.py
src/distllm/core/performance_baseline.py
src/distllm/core/persistence.py
src/distllm/core/persistent_store.py
src/distllm/core/pipeline_composer.py
src/distllm/core/pipeline_executor.py
src/distllm/core/pipeline_orchestrator.py
src/distllm/core/pipeline_overlap.py
src/distllm/core/placement.py
src/distllm/core/plugin_marketplace.py
src/distllm/core/plugin_sandbox.py
src/distllm/core/plugin_system.py
src/distllm/core/predictive_cache.py
src/distllm/core/predictive_cache_warming.py
src/distllm/core/predictive_failure.py
src/distllm/core/preemptible_scheduler.py
src/distllm/core/preference_learning.py
src/distllm/core/prefix_cache.py
src/distllm/core/pricing_providers.py
src/distllm/core/priority_heap.py
src/distllm/core/privacy_budget.py
src/distllm/core/prompt_caching_service.py
src/distllm/core/prompt_library.py
src/distllm/core/protocols.py
src/distllm/core/provider_health.py
src/distllm/core/provisioning.py
src/distllm/core/pulse_performance_model.py
src/distllm/core/quantization_selector.py
src/distllm/core/radix_tree_cache.py
src/distllm/core/rebalancer.py
src/distllm/core/redis_prompt_cache.py
src/distllm/core/replication_controller.py
src/distllm/core/request_auditor.py
src/distllm/core/request_fingerprinting.py
src/distllm/core/request_latency.py
src/distllm/core/request_pipeline.py
src/distllm/core/request_replay.py
src/distllm/core/request_tracker.py
src/distllm/core/resource_manager.py
src/distllm/core/route_audit.py
src/distllm/core/routing_extensions.py
src/distllm/core/schedule_simulator.py
src/distllm/core/schedule_viz.py
src/distllm/core/secret_manager.py
src/distllm/core/semantic_cache.py
src/distllm/core/sentinel_qos.py
src/distllm/core/shadow_eval_runner.py
src/distllm/core/shared_layer_pool.py
src/distllm/core/smart_model_router.py
src/distllm/core/spec_equivalence.py
src/distllm/core/spec_verify.py
src/distllm/core/speculative_adaptor.py
src/distllm/core/speculative_dashboard.py
src/distllm/core/speculative_decoder.py
src/distllm/core/speculative_profiler.py
src/distllm/core/split_brain.py
src/distllm/core/spot_failover.py
src/distllm/core/spot_forecasting.py
src/distllm/core/starvation_monitor.py
src/distllm/core/state_replication.py
src/distllm/core/stats_collector.py
src/distllm/core/step_processor.py
src/distllm/core/straggler_alerts.py
src/distllm/core/straggler_aware_scheduler.py
src/distllm/core/straggler_detector.py
src/distllm/core/streaming_cost.py
src/distllm/core/streaming_generator.py
src/distllm/core/subsystem_registry.py
src/distllm/core/synapse_debugger.py
src/distllm/core/synth_data_generator.py
src/distllm/core/telemetry.py
src/distllm/core/tenant_billing.py
src/distllm/core/tenant_cost_attribution.py
src/distllm/core/token_generator.py
src/distllm/core/token_streaming_buffer.py
src/distllm/core/topology_aware_lb.py
src/distllm/core/topology_aware_tiering.py
src/distllm/core/tree_speculative_decoder.py
src/distllm/core/types.py
src/distllm/core/unified_router.py
src/distllm/core/unified_sla_router.py
src/distllm/core/usage_meter.py
src/distllm/core/vllm_backend.py
src/distllm/core/vllm_node.py
src/distllm/core/voyager_multimodal.py
src/distllm/core/webgpu_manager.py
src/distllm/core/webhook_formatters.py
src/distllm/core/webhook_manager.py
src/distllm/core/wisp_wasm.py
src/distllm/core/workload_classifier.py
src/distllm/core/advanced_scheduling/__init__.py
src/distllm/core/advanced_scheduling/cost_aware.py
src/distllm/core/advanced_scheduling/disaggregated.py
src/distllm/core/advanced_scheduling/energy.py
src/distllm/core/advanced_scheduling/federated.py
src/distllm/core/advanced_scheduling/heterogeneous.py
src/distllm/core/advanced_scheduling/multi_objective.py
src/distllm/core/advanced_scheduling/policy.py
src/distllm/core/advanced_scheduling/predictive.py
src/distllm/core/advanced_scheduling/preemption.py
src/distllm/core/advanced_scheduling/tiered_store.py
src/distllm/core/advanced_scheduling/token_bank.py
src/distllm/core/advanced_scheduling/wan.py
src/distllm/core/dp_inference/__init__.py
src/distllm/core/dp_inference/accounting.py
src/distllm/core/dp_inference/config.py
src/distllm/core/dp_inference/mechanisms.py
src/distllm/core/evaluation/__init__.py
src/distllm/core/evaluation/constants.py
src/distllm/core/evaluation/db.py
src/distllm/core/evaluation/formatters.py
src/distllm/core/evaluation/loaders.py
src/distllm/core/evaluation/models.py
src/distllm/core/evaluation/report.py
src/distllm/core/evaluation/runner.py
src/distllm/core/evaluation/scorers.py
src/distllm/core/evaluation/worker.py
src/distllm/core/plugins/__init__.py
src/distllm/core/plugins/sandbox.py
src/distllm/core/scheduler/__init__.py
src/distllm/core/scheduler/budget.py
src/distllm/core/scheduler/budget_computer.py
src/distllm/core/scheduler/chunked_prefill.py
src/distllm/core/scheduler/kv_cache_manager.py
src/distllm/core/scheduler/preemption_manager.py
src/distllm/core/scheduler/pressure.py
src/distllm/core/scheduler/sequence.py
src/distllm/core/structured_output/__init__.py
src/distllm/core/structured_output/config.py
src/distllm/core/structured_output/engine.py
src/distllm/core/structured_output/streaming.py
src/distllm/core/structured_output/validator.py
src/distllm/core/vectorstore/__init__.py
src/distllm/core/vectorstore/base.py
src/distllm/core/vectorstore/chroma_store.py
src/distllm/core/vectorstore/factory.py
src/distllm/core/vectorstore/pgvector_store.py
src/distllm/core/vectorstore/qdrant_store.py
src/distllm/core/vectorstore/rag.py
src/distllm/core/vectorstore/providers/__init__.py
src/distllm/core/vectorstore/providers/milvus.py
src/distllm/core/vectorstore/providers/pinecone.py
src/distllm/core/vectorstore/providers/qdrant.py
src/distllm/core/vectorstore/providers/weaviate.py
src/distllm/dashboard/__init__.py
src/distllm/dashboard/verification_history.py
src/distllm/dashboard/ws_handler.py
src/distllm/dist/__init__.py
src/distllm/dist/__init__.pyi
src/distllm/dist/adaptive_speculator.py
src/distllm/dist/admin_cli.py
src/distllm/dist/api_docs.py
src/distllm/dist/async_pipeline.py
src/distllm/dist/attention.py
src/distllm/dist/attention_block_pool.py
src/distllm/dist/attention_distributed.py
src/distllm/dist/autoscaler.py
src/distllm/dist/block_pool.py
src/distllm/dist/block_transfer_service.py
src/distllm/dist/byzantine.py
src/distllm/dist/cache.py
src/distllm/dist/cache_digest.py
src/distllm/dist/chunked_prefill.py
src/distllm/dist/cloud_selector.py
src/distllm/dist/config.py
src/distllm/dist/cross_cluster.py
src/distllm/dist/daas_server.py
src/distllm/dist/discovery.py
src/distllm/dist/draft_bank.py
src/distllm/dist/draft_migration.py
src/distllm/dist/ebpf_transport.py
src/distllm/dist/edge_cloud.py
src/distllm/dist/edge_federation.py
src/distllm/dist/execution_planner.py
src/distllm/dist/federated_merge.py
src/distllm/dist/federation.py
src/distllm/dist/flash_attention.py
src/distllm/dist/fsdp.py
src/distllm/dist/geo.py
src/distllm/dist/ice_transport.py
src/distllm/dist/kv_migration.py
src/distllm/dist/latency.py
src/distllm/dist/lifecycle.py
src/distllm/dist/marketplace.py
src/distllm/dist/merkle.py
src/distllm/dist/metrics.py
src/distllm/dist/model_store.py
src/distllm/dist/multi_tenant.py
src/distllm/dist/multimodal.py
src/distllm/dist/nat.py
src/distllm/dist/nccl.py
src/distllm/dist/network.py
src/distllm/dist/node_client.py
src/distllm/dist/node_pb2.py
src/distllm/dist/node_pb2.pyi
src/distllm/dist/node_pb2_grpc.py
src/distllm/dist/node_pb2_grpc.pyi
src/distllm/dist/node_registrar.py
src/distllm/dist/node_service.py
src/distllm/dist/observability.py
src/distllm/dist/otel.py
src/distllm/dist/p2p_model_distributor.py
src/distllm/dist/paged_attention_kernel.py
src/distllm/dist/parallel.py
src/distllm/dist/parallel_planner.py
src/distllm/dist/parallel_topology.py
src/distllm/dist/power_cap.py
src/distllm/dist/predictive_cache.py
src/distllm/dist/preemption.py
src/distllm/dist/prefix_cache.py
src/distllm/dist/prefix_clustering.py
src/distllm/dist/privacy.py
src/distllm/dist/provisioning.py
src/distllm/dist/quality.py
src/distllm/dist/quic_transport.py
src/distllm/dist/quota_enforcer.py
src/distllm/dist/rebalancer.py
src/distllm/dist/recovery.py
src/distllm/dist/recovery_drill.py
src/distllm/dist/redis_cache.py
src/distllm/dist/redundant.py
src/distllm/dist/redundant_executor.py
src/distllm/dist/reputation.py
src/distllm/dist/router.py
src/distllm/dist/straggler.py
src/distllm/dist/streaming_kv_transfer.py
src/distllm/dist/tensor_pool.py
src/distllm/dist/tgi_compat.py
src/distllm/dist/topology.py
src/distllm/dist/topology_consensus.py
src/distllm/dist/topology_dynamic.py
src/distllm/dist/tp_inprocess.py
src/distllm/dist/tp_launcher.py
src/distllm/dist/tracing.py
src/distllm/dist/transport.py
src/distllm/dist/wan_speculative.py
src/distllm/dist/wandb_integration.py
src/distllm/dist/webrtc.py
src/distllm/dist/wide_area.py
src/distllm/dist/worker.py
src/distllm/dist/zero_copy.py
src/distllm/dist/backends/__init__.py
src/distllm/dist/backends/backend_profiles.py
src/distllm/dist/backends/graceful_degradation.py
src/distllm/dist/backends/health_monitor.py
src/distllm/dist/backends/llamacpp.py
src/distllm/dist/backends/ray.py
src/distllm/dist/backends/vllm.py
src/distllm/dist/chaos/__init__.py
src/distllm/dist/chaos/chaos_orchestrator.py
src/distllm/dist/chaos/fault_injector.py
src/distllm/dist/daas/__init__.py
src/distllm/dist/daas/load_balancer.py
src/distllm/dist/daas/marketplace_integration.py
src/distllm/dist/daas/resource_isolation.py
src/distllm/dist/daas/tenant_dispatcher.py
src/distllm/dist/daas/usage_meter.py
src/distllm/dist/disagg/__init__.py
src/distllm/dist/disagg/pool.py
src/distllm/dist/disagg/transfer.py
src/distllm/dist/disagg/transfer_compression.py
src/distllm/dist/disagg/transfer_engine.py
src/distllm/dist/p2p/__init__.py
src/distllm/dist/p2p/discovery.py
src/distllm/dist/p2p/gossip.py
src/distllm/dist/p2p/kademlia_dht.py
src/distllm/dist/p2p/load_balancer.py
src/distllm/dist/p2p/quic_transport.py
src/distllm/dist/p2p/router.py
src/distllm/dist/p2p/transport.py
src/distllm/dist/partition/__init__.py
src/distllm/dist/partition/adaptive.py
src/distllm/dist/partition/benchmark_suite.py
src/distllm/dist/partition/cli.py
src/distllm/dist/partition/cloud_arbitrage.py
src/distllm/dist/partition/config.py
src/distllm/dist/partition/cost_model.py
src/distllm/dist/partition/learned_cost.py
src/distllm/dist/partition/mixed_precision_tuner.py
src/distllm/dist/partition/network_cost_model.py
src/distllm/dist/partition/optimizer.py
src/distllm/dist/partition/pareto_optimizer.py
src/distllm/dist/partition/partitioner.py
src/distllm/dist/partition/persistence.py
src/distllm/dist/partition/plugins.py
src/distllm/dist/partition/profiles.py
src/distllm/dist/partition/quant_bench.py
src/distllm/dist/partition/quant_calibrate.py
src/distllm/dist/partition/quant_coordinator.py
src/distllm/dist/partition/quant_cost.py
src/distllm/dist/partition/quant_partition.py
src/distllm/dist/partition/quant_report.py
src/distllm/dist/partition/quantization_metrics.py
src/distllm/dist/partition/quantization_search.py
src/distllm/dist/partition/quantization_tuner.py
src/distllm/dist/partition/topology.py
src/distllm/dist/partition/validator.py
src/distllm/dist/partition/visualizer.py
src/distllm/dist/pipeline/__init__.py
src/distllm/dist/pipeline/bandwidth_controller.py
src/distllm/dist/pipeline/compression_negotiation.py
src/distllm/dist/pipeline/context.py
src/distllm/dist/pipeline/continuous_batching.py
src/distllm/dist/pipeline/disagg_orchestrator.py
src/distllm/dist/pipeline/orchestrator.py
src/distllm/dist/pipeline/pipeline_reconfig.py
src/distllm/dist/pipeline/profiler.py
src/distllm/dist/pipeline/serialization.py
src/distllm/dist/pipeline/simulator.py
src/distllm/dist/pipeline/strategy.py
src/distllm/dist/pipeline/token_accumulator.py
src/distllm/dist/pipeline/transport.py
src/distllm/dist/pipeline/wan_disagg_orchestrator.py
src/distllm/dist/privacy/__init__.py
src/distllm/dist/privacy/privacy_accountant.py
src/distllm/dist/routing/__init__.py
src/distllm/dist/routing/arbitrage_engine.py
src/distllm/dist/routing/composite.py
src/distllm/dist/routing/consistent_hash.py
src/distllm/dist/routing/latency_aware.py
src/distllm/dist/routing/load_aware.py
src/distllm/dist/scheduling/__init__.py
src/distllm/dist/scheduling/batcher.py
src/distllm/dist/scheduling/classifier.py
src/distllm/dist/scheduling/deadline_scheduler.py
src/distllm/dist/scheduling/iteration.py
src/distllm/dist/scheduling/profiler.py
src/distllm/dist/simulation/__init__.py
src/distllm/dist/simulation/chaos_simulator.py
src/distllm/dist/simulation/cluster_simulator.py
src/distllm/dist/simulation/cost_aware_provisioning.py
src/distllm/dist/simulation/digital_twin.py
src/distllm/dist/simulation/topology_optimizer.py
src/distllm/dist/simulation/what_if.py
src/distllm/dist/speculative/__init__.py
src/distllm/dist/speculative/adaptive_spec.py
src/distllm/dist/speculative/draft_cache.py
src/distllm/dist/speculative/draft_orchestrator.py
src/distllm/dist/speculative/draft_registry.py
src/distllm/dist/speculative/multi_draft.py
src/distllm/dist/speculative/online_sisd.py
src/distllm/dist/structured_output/__init__.py
src/distllm/dist/structured_output/engine.py
src/distllm/errors/__init__.py
src/distllm/errors/policies.py
src/distllm/errors/retry.py
src/distllm/errors/types.py
src/distllm/health/__init__.py
src/distllm/health/failover.py
src/distllm/health/prober.py
src/distllm/health/service.py
src/distllm/health/state.py
src/distllm/integrations/__init__.py
src/distllm/integrations/mlflow_tracking.py
src/distllm/integrations/spark_connector.py
src/distllm/integrations/_common/__init__.py
src/distllm/integrations/_common/base_tool_provider.py
src/distllm/integrations/_common/cost_tracker.py
src/distllm/integrations/_common/model_router.py
src/distllm/integrations/ci/__init__.py
src/distllm/integrations/ci/_common.py
src/distllm/integrations/ci/gitlab.py
src/distllm/integrations/ci/jenkins.py
src/distllm/integrations/wandb/__init__.py
src/distllm/models/__init__.py
src/distllm/models/_trust_remote.py
src/distllm/models/adapter.py
src/distllm/models/adapter_router.py
src/distllm/models/cache.py
src/distllm/models/model_hub.py
src/distllm/models/partition_planner.py
src/distllm/models/partitioner.py
src/distllm/models/rope_scaling.py
src/distllm/models/safetensors_index.py
src/distllm/observability/__init__.py
src/distllm/observability/alerting_config.py
src/distllm/observability/capacity_models.py
src/distllm/observability/capacity_planning.py
src/distllm/observability/exporter.py
src/distllm/observability/exporter_datadog.py
src/distllm/observability/health_config.py
src/distllm/observability/incident_response.py
src/distllm/observability/logging.py
src/distllm/observability/logging_config.py
src/distllm/observability/loki_sink.py
src/distllm/observability/metrics.py
src/distllm/observability/metrics_completeness.py
src/distllm/observability/otel_logging.py
src/distllm/observability/self_healing_config.py
src/distllm/observability/slo_config.py
src/distllm/observability/spans.py
src/distllm/observability/tracing.py
src/distllm/observability/tracing_config.py
src/distllm/observability/wandb_monitor.py
src/distllm/plugins/__init__.py
src/distllm/plugins/airflow.py
src/distllm/plugins/auth_plugin.py
src/distllm/plugins/builtin.py
src/distllm/plugins/cache_plugin.py
src/distllm/plugins/health_plugin.py
src/distllm/plugins/kubeflow.py
src/distllm/plugins/mlflow_plugin.py
src/distllm/plugins/registry.py
src/distllm/prompts/__init__.py
src/distllm/prompts/analysis.py
src/distllm/prompts/code.py
src/distllm/prompts/creative.py
src/distllm/prompts/education.py
src/distllm/prompts/engine.py
src/distllm/prompts/exchange.py
src/distllm/prompts/language.py
src/distllm/prompts/library.py
src/distllm/prompts/management.py
src/distllm/prompts/productivity.py
src/distllm/prompts/professional.py
src/distllm/prompts/prompt_def.py
src/distllm/prompts/reasoning.py
src/distllm/prompts/specialized.py
src/distllm/prompts/templates.py
src/distllm/prompts/writing.py
src/distllm/sdk/__init__.py
src/distllm/sdk/circuit_breaker.py
src/distllm/sdk/client.py
src/distllm/sdk/observability.py
src/distllm/sdk/streaming.py
src/distllm/sdk/transport.py
src/distllm/sdk/types.py
src/distllm/security/__init__.py
src/distllm/security/e2e.py
src/distllm/security/edge_attestation.py
src/distllm/security/log_redaction.py
src/distllm/security/quantum_safe_tls.py
src/distllm/security/spiffe.py
src/distllm/security/tee.py
src/distllm/security/utils.py
src/distllm/security/watermark.py
src/distllm/security/content_moderation/__init__.py
src/distllm/security/content_moderation/base.py
src/distllm/security/content_moderation/jailbreak.py
src/distllm/security/content_moderation/pii.py
src/distllm/security/content_moderation/pipeline.py
src/distllm/security/content_moderation/topics.py
src/distllm/security/content_moderation/toxicity.py
src/distllm/terraform/__init__.py
src/distllm/ui/__init__.py
src/distllm/ui/app.py
src/distllm/utils/__init__.py
src/distllm/utils/gbnf_grammar.py
src/distllm/utils/lazy_imports.py
src/distllm/utils/scheduling.py
src/distllm/verification/__init__.py
src/distllm/verification/comparator.py
src/distllm/verification/hash_registry.py
src/distllm/verification/report.py
src/distllm/verification/runner.py
src/distllm/verification/test_verify.py
src/distributed_llm.egg-info/PKG-INFO
src/distributed_llm.egg-info/SOURCES.txt
src/distributed_llm.egg-info/dependency_links.txt
src/distributed_llm.egg-info/entry_points.txt
src/distributed_llm.egg-info/requires.txt
src/distributed_llm.egg-info/top_level.txt
tests/test_c4_ci_testing_extra_regression.py
tests/test_comprehensive.py
tests/test_cross_cloud_router.py
tests/test_cross_platform.py
tests/test_errors_retry.py
tests/test_features_6_1_bugs.py
tests/test_features_autopilot_privacy_plugins.py
tests/test_features_fusion_prefetch.py
tests/test_features_integration_cluster.py
tests/test_features_integrations.py
tests/test_features_modules_5_1.py
tests/test_features_property.py
tests/test_features_release_gates.py
tests/test_features_sla_equivalence.py
tests/test_gpu.py
tests/test_high_severity_fixes.py
tests/test_high_severity_fixes_2.py
tests/test_high_severity_fixes_3.py
tests/test_high_severity_gpu.py
tests/test_integration_full.py
tests/test_l6_ssrf_guard.py
tests/test_marketplace.py
tests/test_medium_money_preempt_dp.py
tests/test_medium_severity_fixes.py
tests/test_medium_severity_fixes_2.py
tests/test_medium_severity_fixes_3.py
tests/test_migrations.py
tests/test_oidc_c2_regression.py
tests/test_pipeline.py
tests/test_replication_controller.py
tests/test_reputation.py
tests/test_review_table_h9_m6_hash.py
tests/test_review_table_m17_m14_router.py
tests/test_routing_chaos.py
tests/test_routing_integration.py
tests/test_routing_performance.py
tests/test_routing_properties.py
tests/test_routing_security.py
tests/test_spec_verify_shared.py
tests/test_speculative_auto.py
tests/test_speculative_verify_index.py
tests/test_stable_hashing.py
tests/test_straggler_comprehensive.py
tests/test_tenant_cost_money.py