Deprecations

ACTION REQUIRED: The following changes require updates to your code, configuration, or deployment manifests before upgrading.

Behavioral DGD/DGDR Promoted to v1beta1 as the Served API (#9235, #9262): The DynamoGraphDeployment, DynamoComponentDeployment, and DynamoGraphDeploymentRequest APIs now serve v1beta1. The v1alpha1 ↔ v1beta1 round-trip conversion is maintained for backward compatibility, but all docs and examples have moved to v1beta1.

Migrate: Update Helm values, Argo manifests, and any inline YAML to reference v1beta1. Existing v1alpha1 resources continue to work via the conversion path during the transition; remove v1alpha1 references at your next deploy.

Behavioral Duration Config Fields Suffixed with Units (#9246): Configuration fields representing durations were renamed to make their units explicit (e.g., *_ttl → *_ttl_secs).

Migrate: Audit your deployment YAMLs and CLI invocations for any duration field; the new suffix-bearing names are required. The previous unsuffixed names are no longer recognized.

Behavioral Concurrent Radix Tree is the Default Approximate Router (#9219, #9007): The default approximate KV routing backend switched to the concurrent radix tree with anchor-aware branch sharding.

Migrate: Update any custom router instrumentation that targeted the previous radix-tree internals. No action required for default deployments; routing semantics are equivalent.

Behavioral Inter-Pod GPU Memory Service Sidecar Model (#7777, #8829): GMS moves to an inter-pod sidecar that multiple workers can share. The Operator gates GMS+Snapshot combinations via Helm config.

Migrate: If you ran the v1.1.0 per-pod GMS deployment pattern, switch to the new shared-sidecar Helm values. The previous topology continues to work but is no longer the recommended path.

Deprecated CUDA 12 Containers Discontinued in v1.3.0: v1.2.0 is the last release to publish CUDA 12 container images. Starting with v1.3.0, Dynamo will ship CUDA 13 images only. In v1.2.0 the vLLM and SGLang containers ship both CUDA 12.9 and CUDA 13.0 variants, while TensorRT-LLM is already CUDA 13 only.

Migrate: Move CUDA 12 deployments to the CUDA 13 container variants before upgrading to v1.3.0.

Deprecated The following warnings from v1.1.0 still apply. Migrate before they are removed:

• v1alpha1 DGDR API: now in active conversion to v1beta1 (see above)
• enableGpuDiscovery CRD field has no effect
• ComponentName field on ServiceReplicaStatus: migrate to ComponentNames
• Router CLI flags without the --router- prefix
• vLLM --is-prefill-worker / --is-decode-worker: migrate to --disaggregation-mode
• --router-durable-kv-events: migrate to the event-plane subscriber

ACTION REQUIRED: The following changes require updates to your code, configuration, or deployment manifests before upgrading.

Behavioral enable_nats and use_kv_events Removed from DistributedRuntime (#7265): Both parameters are removed from DistributedRuntime, create_runtime(), and the dynamo_worker() decorator. NATS is now auto-detected from the event plane: enabled when the request plane is NATS or NATS_SERVER is configured.

Migrate: Drop both arguments from your Python entry points and configure NATS via the DYN_EVENT_PLANE and NATS_SERVER environment variables instead.

Behavioral Experimental nvext.cache_control Cache Pinning Removed (#7790): The experimental cache-pinning feature is removed: the nvext.cache_control request field, the --enable-cache-control flag, and the DYN_ENABLE_CACHE_CONTROL env var are all gone. SGLang upstream chose a different direction, so the v1.0.0 plumbing is being unwound. The Anthropic Messages parser still accepts cache_control blocks for protocol compatibility but no longer derives router-pin TTLs from them.

Migrate: If you depended on cache pinning, track the v1.2.0 sticky-session / session-controller work. There is no drop-in replacement in v1.1.0.

Behavioral Cargo-Built dynamo-kv-indexer Binary Removed (#7338): The Cargo-built dynamo-kv-indexer binary in lib/kv-router/target/release/ is removed; the maturin-built binary shipped via the Python wheel is now the single source.

Migrate: Update launchers and Dockerfiles to point at the wheel-installed dynamo-kv-indexer (on PATH after pip install ai-dynamo).

Behavioral LLaVA-Specific EPD Path Removed; EPD Now Single-GPU (#6674): The LLaVA-specific multimodal EPD code path is removed, EPD is now constrained to single-GPU configurations, and the default multimodal example moved from Llava-Mistral to Qwen/Qwen3-VL-2B-Instruct.

Migrate: Switch LLaVA workloads to the aggregated path or to a Qwen3-VL recipe.

Behavioral Compressed Concurrent Tree Default (#7874): The KV router defaults to the compressed concurrent radix tree. Improves resource utilization for multi-threaded indexing; node-allocation semantics differ from the previous tree.

Migrate: Update any custom instrumentation that targeted the old radix-tree internals. No action required for default deployments.

Behavioral MDC Checksum Scoped Per-WorkerSet (#7368): Model Discovery Card checksum validation moved from per-Model to per-WorkerSet. Different WorkerSets under the same Model can now carry different configuration without forcing workers to drain first.

Migrate: If you relied on the v1.0.0 strict per-Model behavior, audit your WorkerSet configs before upgrading.

Removed vLLM Auto-Enable KV Events Removed (#7591): The deprecated automatic KV-events config in vLLM is removed; the DYN_VLLM_KV_EVENT_PORT env var is also no longer supported.

Migrate: Set --kv-events-config explicitly per the v1.0.0 migration note.

Removed Unused genai-perf Pin Dropped (#8763): The unused genai-perf==0.0.15 pin was removed from container/deps/requirements.benchmark.txt. It was not invoked anywhere in the repo.

Migrate: No action required. aiperf is the supported in-container benchmarking tool.

Deprecated The following warnings from v1.0.0 still apply. Migrate before they are removed:

• v1alpha1 DGDR API: migrate to v1beta1
• enableGpuDiscovery CRD field has no effect
• ComponentName field on ServiceReplicaStatus: migrate to ComponentNames
• Router CLI flags without the --router- prefix
• vLLM --is-prefill-worker/--is-decode-worker: migrate to --disaggregation-mode
• --router-durable-kv-events: migrate to the event-plane subscriber

ACTION REQUIRED: The following changes require updates to your code, configuration, or deployment manifests before upgrading.

Removed KV Router Flags Renamed (#6361): All KV router CLI flags and env vars now use the --router-* / DYN_ROUTER_* prefix.

Migrate: Update all CLI invocations, env vars, and deployment YAMLs to use the new names.

Removed Disagg Flag Inverted (#6515): --enforce-disagg replaced by --decode-fallback with inverted semantics — disaggregated mode is now enforced by default.

Migrate: Replace --enforce-disagg with --decode-fallback. If you need fallback to aggregated mode, explicitly pass --decode-fallback or DYN_DECODE_FALLBACK=true. In the EPP plugin, update from DYN_ENFORCE_DISAGG to DYN_DECODE_FALLBACK with inverted boolean.

Removed Migration Limit Moved to Frontend (#5918): The --migration-limit CLI flag has been removed from all backend workers (vLLM, SGLang, TRT-LLM) and is now set on the Frontend only.

Migrate: Remove --migration-limit from backend launch commands; pass it to the Frontend instead.

Removed Connector Flag Replaced (#6450): The --connector flag is removed. Disaggregated prefill workers now require explicit --kv-transfer-config with a JSON value.

Migrate: Replace --connector nixl with --kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both"}'. Update all deployment YAMLs and launch scripts accordingly.

Behavioral KV Events Now Opt-In (#6404): KV cache events are no longer auto-created when prefix caching is enabled. Users must explicitly opt in via --kv-events-config.

Migrate: Add --kv-events-config '{"publisher":"zmq","endpoint":"tcp://*:20080","enable_kv_cache_events":true}' to worker launch commands. Replace DYN_VLLM_KV_EVENT_PORT env var with the CLI flag.

Behavioral Local Indexer Now Default (#5941, #6073): Default event transport changed from JetStream to NATS Core/Event Plane with Local Indexer. The --enable-local-indexer flag is removed.

Migrate: If you relied on JetStream persistence, add --durable-kv-events on both frontend and all workers. Remove any --enable-local-indexer flags.

Removed Omni Flags Prefixed (#6476): 14 diffusion/omni CLI flags renamed with --omni- prefix (e.g., --enforce-eager → --omni-enforce-eager).

Migrate: Update CLI invocations to use the --omni- prefixed names.

Removed Multimodal Worker Flag Removed (#6060): --multimodal-encode-prefill-worker removed from vLLM backend.

Migrate: Use --multimodal-encode-worker, --multimodal-worker, or --multimodal-decode-worker instead.

Behavioral Output Modalities Required (#6270): vLLM omni mode no longer auto-registers image endpoints; you must pass --output-modalities image explicitly.

Removed Media URL Flags Unified (#6391): SGLang/TRT-LLM flags --image-diffusion-fs-url, --video-generation-fs-url, and --output-dir replaced by --media-fs-url and --media-base-url.

Removed Discovery Backend Simplified (#6167): DYN_DISCOVERY_BACKEND now accepts kubernetes, etcd, file, mem directly. Remove DYN_KV_STORE; replace --store-kv with --discovery-backend.

Removed Planner CLI Replaced by Config File (#6356): All individual Planner CLI flags removed in favor of --config <path> pointing to a JSON/YAML configuration file.

Removed dynamo-run Removed (#6203): The dynamo-run CLI tool and all its flags have been removed. Migrate to the Python-based deployment approach.

Removed Env Var Renames (#6358, #5882):

Removed KVStats Metrics Removed (#5704): dynamo_component_kvstats_* metrics removed. Use dynamo_frontend_inter_token_latency_seconds for Decode autoscaling instead of kvstats_gpu_cache_usage_percent.

Removed Router Metrics Namespace (#6227): dynamo_frontend_worker_active_* → dynamo_router_worker_active_*, dynamo_component_router_* → dynamo_router_*. New router_id label added to all Router metrics.

Behavioral Frontend Request Counter Label (#5568): dynamo_frontend_requests_total now includes an error_type label. Update PromQL queries to account for the new label.

Removed SGLang Metric Prefix (#5701): SGLang metrics now use the native sglang: prefix (colon) instead of sglang_ (underscore).

Behavioral etcd Subchart Disabled (#6329): Bundled etcd is now disabled by default. Set global.etcd.install: true if your deployment depends on it.

Removed Webhook Key Removed (#6441): webhook.enabled removed from Helm values. Remove it from custom values files.

Removed Helm Values Restructured for Snapshot (#5946): storage.signalHostPath, daemonset.criu., and daemonset.containerRuntimeSocket replaced by config.checkpoint. and config.agent.* hierarchy.

Behavioral DGDR Planner Schema (#6463): FeaturesSpec.planner in DGDR CRD changed from a typed PlannerSpec to the PlannerConfig JSON schema. Review DGDR manifests that set features.planner.

Removed EPP Discovery Timeout (#5770): DYN_DISCOVERY_TIMEOUT_SEC no longer works. Use StartupProbe failureThreshold × periodSeconds instead.

Removed Component/Namespace/CancellationToken Removed (#6403, #6386, #6405): Component, Namespace, and CancellationToken classes removed from the Python API.

Migrate: Replace runtime.namespace('ns').component('comp').endpoint('ep') with runtime.endpoint('ns.comp.ep'). Replace token.cancel() with HttpService.shutdown(). Pass DistributedRuntime directly to service .run() methods.

Behavioral Frontend Config Refactored (#6201): Frontend CLI now rejects unknown args unless --chat-processor vllm is set.

Behavioral ModelManager Checksum Enforcement (#6054): Mismatched MDC checksums across WorkerSets now raise ChecksumMismatch instead of being silently accepted.

Behavioral Tool Call Parser Separation (#5849): --tool-call-parser alone no longer uses Dynamo’s parser. Use --dyn-tool-call-parser for Dynamo’s pipeline.

Behavioral Custom Backend Metrics Removed (#5893): custom_backend_metrics_endpoint and custom_backend_metrics_polling_interval removed from LocalModel and frontend config.

Removed Deprecated Component Removals: Removed dynamo-run and mistral-rs engine (#6203), standalone FastAPI Router (#5845), media-nixl feature (#5940), and llava-hf recipes (#6961).

Behavioral Local Indexers On By Default (#5941): KV event transport now defaults to NATS Core/Event Plane with Local Indexer instead of JetStream. Pass --durable-kv-events on both frontend and workers to restore JetStream behavior.

Behavioral GPU Memory Utilization (#5755): gpu-memory-utilization adjusted for vLLM runtime to improve out-of-the-box performance.

Behavioral Operator Env Vars Documented (#6548): All environment variables injected by the Operator are now documented.

Deprecated dynamo-crds Helm Chart: The standalone dynamo-crds Helm chart is deprecated. CRDs are now embedded in the Dynamo Operator image and applied automatically via an init container on the operator Deployment (#6466, #6780). Users should uninstall the dynamo-crds Helm release; the operator manages CRD lifecycle directly.

The following features still work but will be removed in a future release with most targeted to Dynamo v1.1.0.

Deprecated v1alpha1 DGDR API (#6352): The v1alpha1 DynamoGraphDeploymentRequest API will be removed in a future release. Migrate to v1beta1; automatic conversion maintains backward compatibility during the transition.

Deprecated enableGpuDiscovery CRD Field (#6224): The enableGpuDiscovery CRD field no longer has any effect and will be removed in a future release. GPU discovery now runs automatically.

Deprecated ComponentName Field (#6110): The ComponentName field on ServiceReplicaStatus will be removed in a future release. Migrate to the new ComponentNames list field.

Deprecated Router Legacy Flag Names (#6346): Router CLI flags without the --router- prefix (e.g., --block-size, --kv-events) will be removed in a future release. Migrate to the prefixed versions (--router-block-size, --router-kv-events).

Deprecated vLLM KV Auto-Enable (#6404): vLLM’s auto-enabling of KV events when prefix caching is active will be removed in a future release. Use --kv-events-config explicitly instead.

Deprecated Prefill/Decode Worker Flags (#6483): The --is-prefill-worker and --is-decode-worker boolean flags for the vLLM backend will be removed in a future release. Migrate to --disaggregation-mode.

Deprecated Durable KV Events (#6477): The --router-durable-kv-events CLI flag will be removed in a future release. Migrate to the event-plane subscriber (local_indexer mode).