Skip to content

docs: align documentation paths with site structure - #12373

Merged
dagil-nvidia merged 1 commit into
ai-dynamo:mainfrom
Jont828:docs-folder-restructure
Jul 31, 2026
Merged

docs: align documentation paths with site structure#12373
dagil-nvidia merged 1 commit into
ai-dynamo:mainfrom
Jont828:docs-folder-restructure

Conversation

@Jont828

@Jont828 Jont828 commented Jul 29, 2026

Copy link
Copy Markdown
Contributor

Overview

Reorganize the Fern documentation sources so their filesystem paths mirror the site navigation and use predictable kebab-case names.

Summary

  • Move published pages into stable content-area directories such as kubernetes/, cli/, features/, developer-guide/, and reference/.
  • Rename files to match their sidebar purpose, including renaming both Model Deployment landing pages to overview.mdx and labeling them Overview.
  • Update navigation, redirects, internal links, repository references, documentation tooling, CODEOWNERS, and CI path filters for the new locations.
  • Preserve old published URLs with Fern redirects where URLs intentionally changed.
  • Keep the old-to-new source-file mapping out of the published docs tree; an exhaustive mapping is posted in a PR comment below so contributors can rebase open documentation PRs after this merges.

Details

The source tree now follows the major Fern tabs and sections instead of accumulating pages in legacy top-level buckets. This makes a page's location inferable from its tab, section, and sidebar title while keeping navigation presentation controlled by docs/fern/index.yml.

For contributors with open PRs, see the Old-to-new file mapping for rebasing comment on this PR. It lists the previous and new paths for every moved published page, including translated pages.

Where should the reviewer start?

  1. docs/fern/index.yml for the reorganized navigation paths.
  2. docs/fern/docs.yml for URL continuity redirects.
  3. The old-to-new mapping comment for migration completeness.
  4. .github/filters.yaml, .github/workflows/fern-docs.yml, and .github/codeowners/areas.yaml for repository automation updates.

Validation

  • fern check — 0 errors
  • fern docs broken-links — all checks passed
  • git diff --check — passed

Related Issues

🚫 This PR is NOT linked to an issue:

  • Confirmed — no related issue

Open in Devin Review

@Jont828
Jont828 requested review from a team as code owners July 29, 2026 18:08
@Jont828

Jont828 commented Jul 29, 2026

Copy link
Copy Markdown
Contributor Author

This comment is the migration aid for contributors rebasing documentation PRs after this folder restructure merges.

After rebasing onto upstream/main, find a conflicted old path in the single copyable block below and apply the change to the corresponding new path. Git may detect many moves automatically, but this mapping is authoritative when rename detection is ambiguous. Repeated old paths intentionally indicate tab-local copies.

Updated July 31, 2026 to match the squashed PR head. It includes the AI Simulate/Spica page set, the new sidecar and standalone-router pages, Use Cases paths, the vanilla-vLLM on-ramp, and translated-page moves. The current navigation has 332 entries backed by 328 unique page files.

The block contains 346 old-to-new path pairs, including 13 translated-page pairs.

REBASE WORKFLOW
git fetch upstream
git rebase upstream/main

OLD FILE	NEW FILE
docs/fern/README.md	docs/fern/pages/community/contributing/documentation/building-and-publishing.md
docs/fern/agents/README.md	docs/fern/pages/use-cases/agents/overview.md
docs/fern/agents/agent-harnesses.mdx	docs/fern/pages/use-cases/agents/agent-harnesses.mdx
docs/fern/agents/agent-hints.md	docs/fern/pages/use-cases/agents/agent-hints.md
docs/fern/agents/agent-replay.mdx	docs/fern/pages/use-cases/agents/agent-simulation.mdx
docs/fern/agents/agent-tracing.md	docs/fern/pages/use-cases/agents/agent-tracing.md
docs/fern/agents/priority-scheduling.md	docs/fern/pages/use-cases/agents/priority-scheduling.md
docs/fern/agents/session-ids.mdx	docs/fern/pages/use-cases/agents/session-ids.mdx
docs/fern/agents/thunderagent-router.md	docs/fern/pages/use-cases/agents/thunderagent-program-scheduler.md
docs/fern/api/nixl-connect/README.mdx	docs/fern/pages/reference/nixl-connect/overview.mdx
docs/fern/api/nixl-connect/connector.mdx	docs/fern/pages/reference/nixl-connect/connector.mdx
docs/fern/api/nixl-connect/descriptor.mdx	docs/fern/pages/reference/nixl-connect/descriptor.mdx
docs/fern/api/nixl-connect/device-kind.mdx	docs/fern/pages/reference/nixl-connect/device-kind.mdx
docs/fern/api/nixl-connect/device.mdx	docs/fern/pages/reference/nixl-connect/device.mdx
docs/fern/api/nixl-connect/operation-status.mdx	docs/fern/pages/reference/nixl-connect/operation-status.mdx
docs/fern/api/nixl-connect/rdma-metadata.mdx	docs/fern/pages/reference/nixl-connect/rdma-metadata.mdx
docs/fern/api/nixl-connect/read-operation.mdx	docs/fern/pages/reference/nixl-connect/read-operation.mdx
docs/fern/api/nixl-connect/readable-operation.mdx	docs/fern/pages/reference/nixl-connect/readable-operation.mdx
docs/fern/api/nixl-connect/writable-operation.mdx	docs/fern/pages/reference/nixl-connect/writable-operation.mdx
docs/fern/api/nixl-connect/write-operation.mdx	docs/fern/pages/reference/nixl-connect/write-operation.mdx
docs/fern/backends/mocker_backend/README.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/mocker/rust-backend.md
docs/fern/backends/sglang/README.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/sglang/overview.md
docs/fern/backends/sglang/agents.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/sglang/agents-on-sglang.md
docs/fern/backends/sglang/sglang-chat-processor.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/sglang/chat-processor.md
docs/fern/backends/sglang/sglang-config-reference.mdx	docs/fern/pages/reference/backends/sglang-configuration.mdx
docs/fern/backends/sglang/sglang-disaggregation.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/sglang/disaggregation.md
docs/fern/backends/sglang/sglang-examples.mdx	docs/fern/pages/recipes/cli-templates/sglang.mdx
docs/fern/backends/sglang/sglang-hicache.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/sglang/hicache.md
docs/fern/backends/sglang/sglang-logits-processing.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/sglang/logits-processing.md
docs/fern/backends/sglang/sglang-observability.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/sglang/observability.md
docs/fern/backends/sglang/sglang-reference-guide.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/sglang/reference-guide.md
docs/fern/backends/sglang/sidecar.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/sglang/sidecar.md
docs/fern/backends/trtllm/README.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/tensorrt-llm/overview.md
docs/fern/backends/trtllm/multinode/trtllm-multinode-examples.md	docs/fern/pages/developer-guide/additional-resources/tensorrt-llm-details/multinode-examples.md
docs/fern/backends/trtllm/sidecar.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/tensorrt-llm/sidecar.md
docs/fern/backends/trtllm/trtllm-building-custom-container.md	docs/fern/pages/developer-guide/additional-resources/tensorrt-llm-details/building-a-custom-container.md
docs/fern/backends/trtllm/trtllm-config-reference.mdx	docs/fern/pages/reference/backends/tensorrt-llm-configuration.mdx
docs/fern/backends/trtllm/trtllm-dp-rank-routing.md	docs/fern/pages/developer-guide/additional-resources/tensorrt-llm-details/dp-rank-routing.md
docs/fern/backends/trtllm/trtllm-examples.mdx	docs/fern/pages/recipes/cli-templates/tensorrt-llm.mdx
docs/fern/backends/trtllm/trtllm-gemma3-sliding-window-attention.md	docs/fern/pages/developer-guide/additional-resources/tensorrt-llm-details/gemma3-sliding-window.md
docs/fern/backends/trtllm/trtllm-gpt-oss.md	docs/fern/pages/developer-guide/additional-resources/tensorrt-llm-details/gpt-oss.md
docs/fern/backends/trtllm/trtllm-known-issues.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/tensorrt-llm/known-issues.md
docs/fern/backends/trtllm/trtllm-kv-cache-transfer.md	docs/fern/pages/developer-guide/additional-resources/tensorrt-llm-details/kv-cache-transfer.md
docs/fern/backends/trtllm/trtllm-llama4-plus-eagle.md	docs/fern/pages/developer-guide/additional-resources/tensorrt-llm-details/llama4-plus-eagle.md
docs/fern/backends/trtllm/trtllm-logits-processing.md	docs/fern/pages/developer-guide/additional-resources/tensorrt-llm-details/logits-processing.md
docs/fern/backends/trtllm/trtllm-observability.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/tensorrt-llm/observability.md
docs/fern/backends/trtllm/trtllm-reference-guide.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/tensorrt-llm/reference-guide.md
docs/fern/backends/vllm/README.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/vllm/overview.md
docs/fern/backends/vllm/sidecar.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/vllm/sidecar.md
docs/fern/backends/vllm/vllm-chat-processor.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/vllm/chat-processor.md
docs/fern/backends/vllm/vllm-config-reference.mdx	docs/fern/pages/reference/backends/vllm-configuration.mdx
docs/fern/backends/vllm/vllm-examples.mdx	docs/fern/pages/recipes/cli-templates/vllm.mdx
docs/fern/backends/vllm/vllm-kv-offloading.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/vllm/kv-cache-offloading.md
docs/fern/backends/vllm/vllm-logits-processing.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/vllm/logits-processing.md
docs/fern/backends/vllm/vllm-native-kv-offloading.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/vllm/native-kv-offloading.md
docs/fern/backends/vllm/vllm-observability.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/vllm/observability.md
docs/fern/backends/vllm/vllm-omni-config-reference.mdx	docs/fern/pages/reference/backends/vllm-omni-configuration.mdx
docs/fern/backends/vllm/vllm-reference-guide.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/vllm/reference-guide.md
docs/fern/benchmarks/README.mdx	docs/fern/pages/recipes/feature-benchmarks/browse-all-benchmarks.mdx
docs/fern/benchmarks/benchmarking.md	docs/fern/pages/recipes/feature-benchmarks/benchmarking-guide.md
docs/fern/benchmarks/deepseek-v3-2-wideep-routing.mdx	docs/fern/pages/recipes/feature-benchmarks/deepseek-v3-2-wideep-routing.mdx
docs/fern/benchmarks/embedding_cache.md	docs/fern/pages/recipes/feature-benchmarks/embedding-cache.md
docs/fern/benchmarks/kimi-k2-5-feature-stack.mdx	docs/fern/pages/recipes/feature-benchmarks/agentic-coding-throughput-stack-kimi-k2-5.mdx
docs/fern/benchmarks/kv-router-ab-testing.md	docs/fern/pages/recipes/feature-benchmarks/kv-router-a-b-testing.md
docs/fern/benchmarks/llama-3-70b-topology.mdx	docs/fern/pages/recipes/feature-benchmarks/llama-3-3-70b-topology.mdx
docs/fern/benchmarks/mocker-trace-replay.md	docs/fern/pages/recipes/feature-benchmarks/mocker-trace-replay.md
docs/fern/benchmarks/planner-replay-benchmarking.md	docs/fern/pages/recipes/feature-benchmarks/planner-replay-benchmarking.md
docs/fern/benchmarks/qwen3-32b-kv-routing.mdx	docs/fern/pages/recipes/feature-benchmarks/qwen3-32b-kv-routing-a-b.mdx
docs/fern/benchmarks/qwen3-6-35b-feature-stack.mdx	docs/fern/pages/recipes/feature-benchmarks/qwen3-6-35b-feature-stack.mdx
docs/fern/benchmarks/qwen3-vl-embedding-cache.mdx	docs/fern/pages/recipes/feature-benchmarks/qwen3-vl-embedding-cache.mdx
docs/fern/cli/aiconfigurator.mdx	docs/fern/pages/cli/disaggregated-serving/sizing-with-aiconfigurator.mdx
docs/fern/cli/aiperf.mdx	docs/fern/pages/cli/operations/benchmarking-with-aiperf.mdx
docs/fern/cli/disaggregated-serving.mdx	docs/fern/pages/cli/disaggregated-serving/overview.mdx
docs/fern/cli/introduction.mdx	docs/fern/pages/cli/getting-started/introduction.mdx
docs/fern/cli/kv-cache-offloading.mdx	docs/fern/pages/cli/kv-cache-offloading/overview.mdx
docs/fern/cli/kv-routing.mdx	docs/fern/pages/cli/kv-aware-routing/overview.mdx
docs/fern/cli/multinode-deployment.mdx	docs/fern/pages/cli/model-deployment/multi-node-deployment.mdx
docs/fern/cli/observability.mdx	docs/fern/pages/cli/installation/observability.mdx
docs/fern/cli/overview.mdx	docs/fern/pages/cli/model-deployment/introduction.mdx
docs/fern/community/README.mdx	docs/fern/pages/community/community.mdx
docs/fern/components/aisimulate/README.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/ai-simulate-experimental/overview.md
docs/fern/components/aisimulate/spica/README.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/ai-simulate-experimental/spica-experimental/overview.md
docs/fern/components/aisimulate/spica/examples/glm5-disagg-pareto-frontier-sweep.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/ai-simulate-experimental/spica-experimental/glm-5-fp8-pareto-sweep.md
docs/fern/components/aisimulate/spica/examples/planner-goodput-per-gpu-sweep.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/ai-simulate-experimental/spica-experimental/planner-goodput-per-gpu-sweep.md
docs/fern/components/aisimulate/spica/examples/router-e2e-latency-sweep.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/ai-simulate-experimental/spica-experimental/router-end-to-end-latency-sweep.md
docs/fern/components/aisimulate/spica/optimization-goal.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/ai-simulate-experimental/spica-experimental/optimization-goals.md
docs/fern/components/aisimulate/spica/overview.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/ai-simulate-experimental/spica-experimental/search-flow.md
docs/fern/components/aisimulate/spica/sample.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/ai-simulate-experimental/spica-experimental/unrolled-samples.md
docs/fern/components/aisimulate/spica/search-space.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/ai-simulate-experimental/spica-experimental/search-space.md
docs/fern/components/aisimulate/spica/traffic.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/ai-simulate-experimental/spica-experimental/traffic.md
docs/fern/components/frontend/README.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/frontend/overview.md
docs/fern/components/frontend/Tokenizer.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/frontend/tokenizer.md
docs/fern/components/frontend/frontend-config-reference.mdx	docs/fern/pages/reference/components/frontend-configuration.mdx
docs/fern/components/frontend/frontend-guide.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/frontend/frontend-guide.md
docs/fern/components/frontend/nvext.md	docs/fern/pages/developer-guide/additional-resources/nvidia-request-extensions-nvext.md
docs/fern/components/frontend/python-route-extensions.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/frontend/python-route-extensions.md
docs/fern/components/kvbm/README.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/kvbm/overview.md
docs/fern/components/kvbm/kvbm-config-reference.mdx	docs/fern/pages/reference/components/kvbm-configuration.mdx
docs/fern/components/kvbm/kvbm-guide.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/kvbm/kvbm-guide.md
docs/fern/components/mocker/mocker-cli-reference.mdx	docs/fern/pages/reference/components/mocker-cli-reference.mdx
docs/fern/components/mocker/replay-cli-reference.mdx	docs/fern/pages/reference/components/dynosim-replay-cli-reference.mdx
docs/fern/components/mocker/sweep-reference.mdx	docs/fern/pages/reference/components/dynosim-sweep-reference.mdx
docs/fern/components/planner/README.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/planner/overview.md
docs/fern/components/planner/global-planner.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/planner/global-planner-guide.md
docs/fern/components/planner/planner-config-reference.mdx	docs/fern/pages/reference/components/planner-configuration.mdx
docs/fern/components/planner/planner-examples.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/planner/planner-examples.md
docs/fern/components/planner/planner-guide.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/planner/planner-guide.md
docs/fern/components/profiler/README.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/profiler/overview.md
docs/fern/components/profiler/profiler-config-reference.mdx	docs/fern/pages/reference/components/profiler-configuration.mdx
docs/fern/components/profiler/profiler-examples.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/profiler/profiler-examples.md
docs/fern/components/profiler/profiler-guide.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/profiler/profiler-guide.md
docs/fern/components/router/README.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/overview.md
docs/fern/components/router/deficit-round-robin.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/deficit-round-robin.md
docs/fern/components/router/gateway-api-reference.mdx	docs/fern/pages/reference/components/gateway-api-routing.mdx
docs/fern/components/router/global-router-config-reference.mdx	docs/fern/pages/reference/components/global-router-configuration.mdx
docs/fern/components/router/kv-event-replay-comparison.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/kv-event-replay-comparison.md
docs/fern/components/router/multi-dc-kv-routing.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/multi-dc-kv-routing.md
docs/fern/components/router/router-concepts.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/routing-concepts.md
docs/fern/components/router/router-configuration.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/configuration-and-tuning.md
docs/fern/components/router/router-disaggregated-serving.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/disaggregated-serving.md
docs/fern/components/router/router-examples.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/router-examples.md
docs/fern/components/router/router-filtering.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/worker-filtering.md
docs/fern/components/router/router-guide.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/router-guide.md
docs/fern/components/router/router-offloading.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/offloading-support-matrix.md
docs/fern/components/router/router-operations.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/router-operations.md
docs/fern/components/router/router-testing.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/router-testing.md
docs/fern/components/router/standalone-indexer.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/standalone-indexer.md
docs/fern/components/router/standalone-router.md	docs/fern/pages/cli/kv-aware-routing/standalone-router.md
docs/fern/components/router/standalone-router.md	docs/fern/pages/kubernetes/kv-aware-routing/standalone-router.md
docs/fern/components/router/standalone-selection.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/standalone-selection.md
docs/fern/components/router/standalone-slot-tracker.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/standalone-slot-tracker.md
docs/fern/components/router/topology-aware-kv-transfer.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/topology-aware-kv-transfer.md
docs/fern/contributing/code-quality.md	docs/fern/pages/community/contributing/code-quality.md
docs/fern/contributing/contribution-flow.mdx	docs/fern/pages/community/contributing/contribution-flow.mdx
docs/fern/contributing/dco-and-licensing.md	docs/fern/pages/community/contributing/dco-and-licensing.md
docs/fern/contributing/getting-started.mdx	docs/fern/pages/community/contributing/getting-started.mdx
docs/fern/contribution-guide.md	docs/fern/pages/community/contributing/overview.md
docs/fern/design-docs/architecture.md	docs/fern/pages/developer-guide/knowledge-base/overview.md
docs/fern/design-docs/disagg-serving.md	docs/fern/pages/developer-guide/knowledge-base/concepts/system-architecture/disaggregated-serving.md
docs/fern/design-docs/discovery-plane.md	docs/fern/pages/developer-guide/knowledge-base/concepts/communication-planes/discovery-plane.md
docs/fern/design-docs/distributed-runtime.md	docs/fern/pages/developer-guide/knowledge-base/concepts/system-architecture/distributed-runtime.md
docs/fern/design-docs/dynamo-flow.md	docs/fern/pages/developer-guide/knowledge-base/concepts/system-architecture/architecture-flow.md
docs/fern/design-docs/dynosim-architecture.md	docs/fern/pages/developer-guide/knowledge-base/concepts/simulation/dynosim-architecture.md
docs/fern/design-docs/event-plane.md	docs/fern/pages/developer-guide/knowledge-base/concepts/communication-planes/event-plane.md
docs/fern/design-docs/fault-tolerance-testing.md	docs/fern/pages/developer-guide/knowledge-base/concepts/fault-tolerance/fault-tolerance-testing.md
docs/fern/design-docs/gateway-api-routing.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/kubernetes-operator/gateway-api-routing.md
docs/fern/design-docs/graceful-shutdown.md	docs/fern/pages/developer-guide/knowledge-base/concepts/fault-tolerance/graceful-shutdown-architecture.md
docs/fern/design-docs/kvbm-design.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/kvbm/kvbm-design.md
docs/fern/design-docs/mocker-architecture.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/mocker/mocker-engine-architecture.md
docs/fern/design-docs/observability.md	docs/fern/pages/developer-guide/knowledge-base/concepts/observability-architecture.md
docs/fern/design-docs/planner-design.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/planner/planner-design.md
docs/fern/design-docs/request-cancellation.md	docs/fern/pages/developer-guide/knowledge-base/concepts/fault-tolerance/request-cancellation-architecture.md
docs/fern/design-docs/request-migration.md	docs/fern/pages/developer-guide/knowledge-base/concepts/fault-tolerance/request-migration-architecture.md
docs/fern/design-docs/request-plane.md	docs/fern/pages/developer-guide/knowledge-base/concepts/communication-planes/request-plane.md
docs/fern/design-docs/request-rejection.md	docs/fern/pages/developer-guide/knowledge-base/concepts/fault-tolerance/request-rejection-architecture.md
docs/fern/design-docs/router-design.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/router/router-design.md
docs/fern/design-docs/sidecar-backends.md	docs/fern/pages/developer-guide/knowledge-base/concepts/system-architecture/sidecar-backends.md
docs/fern/design-docs/sidecar-backends.md	docs/fern/pages/kubernetes/model-deployment/sidecar-backends.md
docs/fern/design-docs/vllm-omni-disaggregated.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/vllm/vllm-omni-disaggregated-serving.md
docs/fern/development/backend-guide.md	docs/fern/pages/developer-guide/advanced-customizations/writing-custom-backends/writing-python-workers.md
docs/fern/development/custom-backend.md	docs/fern/pages/developer-guide/advanced-customizations/writing-custom-backends/custom-backend-overview.md
docs/fern/development/custom-containers.md	docs/fern/pages/developer-guide/advanced-customizations/writing-custom-backends/runtime-containers.md
docs/fern/development/jail-stream.md	docs/fern/pages/developer-guide/additional-resources/jail-stream.md
docs/fern/development/runtime-guide.md	docs/fern/pages/developer-guide/additional-resources/runtime-development-guide.md
docs/fern/development/unified-backends.md	docs/fern/pages/developer-guide/advanced-customizations/writing-custom-backends/writing-unified-backends.md
docs/fern/digest/README.md	docs/fern/pages/blog/README.md
docs/fern/digest/agentic-inference/agentic-harnesses.mdx	docs/fern/pages/blog/2026/agentic-harness-support.mdx
docs/fern/digest/agentic-inference/agentic-inference.mdx	docs/fern/pages/blog/2026/agentic-inference-optimizations.mdx
docs/fern/digest/dynosim/dynosim-pareto-frontier.mdx	docs/fern/pages/blog/2026/dynosim-pareto-frontier.mdx
docs/fern/digest/flash-indexer/flash-indexer.mdx	docs/fern/pages/blog/2026/flash-indexer.mdx
docs/fern/digest/index.mdx	docs/fern/pages/blog/latest.mdx
docs/fern/digest/snapshot/dynamo-snapshot-fast-startup.mdx	docs/fern/pages/blog/2026/dynamo-snapshot.mdx
docs/fern/digest/tokenspeed/tokenspeed-day-0.mdx	docs/fern/pages/blog/2026/tokenspeed-day-0-support.mdx
docs/fern/documentation-style-guide.md	docs/fern/pages/community/contributing/documentation/documentation-style-guide.md
docs/fern/dynosim/README.md	docs/fern/pages/cli/operations/simulation-with-dynosim/overview.md
docs/fern/dynosim/README.md	docs/fern/pages/kubernetes/operations/simulation-with-dynosim/overview.md
docs/fern/dynosim/mocker-local.mdx	docs/fern/pages/cli/operations/simulation-with-dynosim/mocker-live-simulation.mdx
docs/fern/dynosim/mocker.mdx	docs/fern/pages/kubernetes/operations/simulation-with-dynosim/mocker-live-simulation.mdx
docs/fern/dynosim/modeling.md	docs/fern/pages/cli/operations/simulation-with-dynosim/simulation-model.md
docs/fern/dynosim/modeling.md	docs/fern/pages/kubernetes/operations/simulation-with-dynosim/simulation-model.md
docs/fern/dynosim/planner-benchmarking.mdx	docs/fern/pages/kubernetes/operations/simulation-with-dynosim/dynosim-planner-replay.mdx
docs/fern/dynosim/runs.mdx	docs/fern/pages/cli/operations/simulation-with-dynosim/dynosim-replay.mdx
docs/fern/dynosim/runs.mdx	docs/fern/pages/kubernetes/operations/simulation-with-dynosim/dynosim-replay.mdx
docs/fern/dynosim/sweeps.mdx	docs/fern/pages/cli/operations/simulation-with-dynosim/dynosim-sweeps.mdx
docs/fern/dynosim/sweeps.mdx	docs/fern/pages/kubernetes/operations/simulation-with-dynosim/dynosim-sweeps.mdx
docs/fern/fault-tolerance/README.md	docs/fern/pages/kubernetes/fault-tolerance/introduction.md
docs/fern/fault-tolerance/graceful-shutdown.md	docs/fern/pages/kubernetes/fault-tolerance/graceful-shutdown.md
docs/fern/fault-tolerance/request-migration.md	docs/fern/pages/kubernetes/fault-tolerance/request-migration.md
docs/fern/fault-tolerance/request-rejection.md	docs/fern/pages/kubernetes/fault-tolerance/request-rejection.md
docs/fern/features/diffusion/README.md	docs/fern/pages/use-cases/diffusion/overview.md
docs/fern/features/diffusion/image-to-video/README.md	docs/fern/pages/use-cases/diffusion/workflows/image-to-video.md
docs/fern/features/diffusion/text-to-audio/README.md	docs/fern/pages/use-cases/diffusion/workflows/text-to-audio.md
docs/fern/features/diffusion/text-to-image/README.md	docs/fern/pages/use-cases/diffusion/workflows/text-to-image.md
docs/fern/features/diffusion/text-to-text/README.md	docs/fern/pages/use-cases/diffusion/workflows/text-to-text-llm-diffusion.md
docs/fern/features/diffusion/text-to-video/README.md	docs/fern/pages/use-cases/diffusion/workflows/text-to-video.md
docs/fern/features/disaggregated-serving/README.md	docs/fern/pages/kubernetes/disaggregated-serving/overview.md
docs/fern/features/disaggregated-serving/aiconfigurator.md	docs/fern/pages/developer-guide/additional-resources/aiconfigurator-reference.md
docs/fern/features/lora/README.md	docs/fern/pages/cli/operations/lora-adapters.md
docs/fern/features/lora/README.md	docs/fern/pages/kubernetes/operations/lora-adapters.md
docs/fern/features/multimodal/README.md	docs/fern/pages/use-cases/multimodal-serving/overview.md
docs/fern/features/multimodal/custom-vision-encoder.md	docs/fern/pages/developer-guide/advanced-customizations/custom-vision-encoders.md
docs/fern/features/multimodal/embedding-cache.md	docs/fern/pages/use-cases/multimodal-serving/embedding-cache.md
docs/fern/features/multimodal/encoder-disaggregation.md	docs/fern/pages/use-cases/multimodal-serving/encoder-disaggregation.md
docs/fern/features/multimodal/multimodal-kv-routing.md	docs/fern/pages/use-cases/multimodal-serving/multimodal-kv-routing.md
docs/fern/features/multimodal/multimodal-sglang.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/sglang/multimodal.md
docs/fern/features/multimodal/multimodal-trtllm.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/tensorrt-llm/multimodal.md
docs/fern/features/multimodal/multimodal-vllm.md	docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/vllm/multimodal.md
docs/fern/features/rl/README.md	docs/fern/pages/use-cases/reinforcement-learning/overview.md
docs/fern/features/speculative-decoding/README.md	docs/fern/pages/developer-guide/additional-resources/speculative-decoding/overview.md
docs/fern/features/speculative-decoding/speculative-decoding-vllm.md	docs/fern/pages/developer-guide/additional-resources/speculative-decoding/speculative-decoding-with-vllm.md
docs/fern/features/tokenizer/README.md	docs/fern/pages/use-cases/fastokens-tokenizer/overview.md
docs/fern/getting-started/building-from-source.md	docs/fern/pages/developer-guide/advanced-customizations/building-from-source.md
docs/fern/getting-started/introduction.mdx	docs/fern/pages/kubernetes/getting-started/introduction.mdx
docs/fern/getting-started/kubernetes-deployment.mdx	docs/fern/pages/kubernetes/model-deployment/introduction.mdx
docs/fern/getting-started/local-installation.mdx	docs/fern/pages/cli/installation/install-dynamo.mdx
docs/fern/getting-started/quickstart.mdx	docs/fern/pages/cli/getting-started/quickstart.mdx
docs/fern/integrations/kv-events-custom-engines.md	docs/fern/pages/developer-guide/advanced-customizations/writing-custom-backends/publish-kv-events.md
docs/fern/kubernetes/api-reference-fern.mdx	docs/fern/pages/reference/kubernetes-api/full-api-reference.mdx
docs/fern/kubernetes/api-reference.md	docs/fern/pages/reference/kubernetes-api/additional-resources/api-reference-k8s.md
docs/fern/kubernetes/auto-deployment-overview.mdx	docs/fern/pages/kubernetes/auto-deployment/overview.mdx
docs/fern/kubernetes/autoscaling.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/kubernetes-operator/autoscaling.md
docs/fern/kubernetes/cloud-providers/aks/aks.mdx	docs/fern/pages/kubernetes/installation/managed-kubernetes/azure/aks-setup.mdx
docs/fern/kubernetes/cloud-providers/aks/azure-lustre-csi.mdx	docs/fern/pages/kubernetes/installation/model-storage/azure-lustre-csi-driver.mdx
docs/fern/kubernetes/cloud-providers/aks/rdma-infiniband.mdx	docs/fern/pages/kubernetes/installation/rdma-setup/infiniband-on-azure.mdx
docs/fern/kubernetes/cloud-providers/aks/spot-vms.mdx	docs/fern/pages/kubernetes/installation/managed-kubernetes/azure/spot-vms.mdx
docs/fern/kubernetes/cloud-providers/aks/storage.md	docs/fern/pages/kubernetes/installation/model-storage/aks-storage.md
docs/fern/kubernetes/cloud-providers/ecs/ecs.mdx	docs/fern/pages/kubernetes/installation/managed-kubernetes/eks/ecs.mdx
docs/fern/kubernetes/cloud-providers/eks/efa.mdx	docs/fern/pages/kubernetes/installation/rdma-setup/efa-on-aws.mdx
docs/fern/kubernetes/cloud-providers/eks/efs.mdx	docs/fern/pages/kubernetes/installation/model-storage/efs.mdx
docs/fern/kubernetes/cloud-providers/eks/eks.mdx	docs/fern/pages/kubernetes/installation/managed-kubernetes/eks/eks-setup.mdx
docs/fern/kubernetes/cloud-providers/gke/gke.mdx	docs/fern/pages/kubernetes/installation/managed-kubernetes/gcp/gke-setup.mdx
docs/fern/kubernetes/cloud-providers/model-storage-overview.md	docs/fern/pages/kubernetes/installation/model-storage/overview.md
docs/fern/kubernetes/cloud-providers/rdma-setup.md	docs/fern/pages/kubernetes/installation/rdma-setup/overview.md
docs/fern/kubernetes/dcd-reference.mdx	docs/fern/pages/reference/kubernetes-api/dynamo-component-deployment.mdx
docs/fern/kubernetes/deployment/dynamomodel-guide.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/kubernetes-operator/managing-models-dynamomodel.md
docs/fern/kubernetes/deployment/minikube.mdx	docs/fern/pages/cli/installation/minikube-setup.mdx
docs/fern/kubernetes/deployment/multinode-deployment.md	docs/fern/pages/kubernetes/model-deployment/multinode-deployments.md
docs/fern/kubernetes/dgd-aiconfigurator.mdx	docs/fern/pages/kubernetes/disaggregated-serving/sizing-with-aiconfigurator.mdx
docs/fern/kubernetes/dgd-expose-frontend.md	docs/fern/pages/kubernetes/model-deployment/expose-the-frontend.md
docs/fern/kubernetes/dgd-guide.md	docs/fern/pages/kubernetes/model-deployment/deploy-with-dgd.md
docs/fern/kubernetes/dgd-intel-xpu.mdx	docs/fern/pages/kubernetes/model-deployment/deploy-on-intel-gpus.mdx
docs/fern/kubernetes/dgd-kv-offloading.mdx	docs/fern/pages/kubernetes/kv-cache-offloading/overview.mdx
docs/fern/kubernetes/dgd-kv-routing.md	docs/fern/pages/kubernetes/kv-aware-routing/dynamo-frontend.md
docs/fern/kubernetes/dgd-reference.mdx	docs/fern/pages/reference/kubernetes-api/dynamo-graph-deployment.mdx
docs/fern/kubernetes/dgdr-guide.md	docs/fern/pages/kubernetes/auto-deployment/auto-deploy-with-dgdr.md
docs/fern/kubernetes/dgdr-planner.mdx	docs/fern/pages/kubernetes/auto-deployment/dynamo-planner.mdx
docs/fern/kubernetes/dgdr-profiler.md	docs/fern/pages/kubernetes/auto-deployment/dynamo-profiler.md
docs/fern/kubernetes/dgdr-reference.mdx	docs/fern/pages/reference/kubernetes-api/dynamo-graph-deployment-request.mdx
docs/fern/kubernetes/disagg-communication-guide.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/kubernetes-operator/disagg-communication.md
docs/fern/kubernetes/dynamo-operator.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/kubernetes-operator/dynamo-operator.md
docs/fern/kubernetes/fast-model-loading.mdx	docs/fern/pages/kubernetes/model-deployment/model-loading/fast-model-loading.mdx
docs/fern/kubernetes/fluxcd.md	docs/fern/pages/developer-guide/additional-resources/fluxcd.md
docs/fern/kubernetes/gateway-api-installation.mdx	docs/fern/pages/kubernetes/installation/gateway-api-routing.mdx
docs/fern/kubernetes/grove.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/multinode/grove.md
docs/fern/kubernetes/inference-gateway.mdx	docs/fern/pages/kubernetes/kv-aware-routing/gateway-api.mdx
docs/fern/kubernetes/installation-guide.md	docs/fern/pages/kubernetes/installation/install-dynamo.md
docs/fern/kubernetes/kv-aware-routing.md	docs/fern/pages/kubernetes/kv-aware-routing/overview.md
docs/fern/kubernetes/lws.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/multinode/lws.md
docs/fern/kubernetes/model-caching-with-fluid.md	docs/fern/pages/developer-guide/additional-resources/model-caching-with-fluid.md
docs/fern/kubernetes/model-caching.mdx	docs/fern/pages/kubernetes/model-deployment/model-loading/model-caching.mdx
docs/fern/kubernetes/modelexpress.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/model-loading/modelexpress.md
docs/fern/kubernetes/multinode-installation.md	docs/fern/pages/kubernetes/installation/multinode-orchestration.md
docs/fern/kubernetes/observability/metrics.mdx	docs/fern/pages/kubernetes/operations/observability.mdx
docs/fern/kubernetes/quickstart.mdx	docs/fern/pages/kubernetes/getting-started/quickstart.mdx
docs/fern/kubernetes/rolling-update.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/kubernetes-operator/rolling-update.md
docs/fern/kubernetes/service-discovery.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/kubernetes-operator/service-discovery.md
docs/fern/kubernetes/shadow-engine-failover.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/kubernetes-operator/shadow-engine-failover.md
docs/fern/kubernetes/snapshot.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/kubernetes-operator/snapshot.md
docs/fern/kubernetes/tilt-dev-setup.md	docs/fern/pages/developer-guide/advanced-customizations/developing-with-tilt.md
docs/fern/kubernetes/topology-aware-kv-transfer.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/multinode/topology-aware-kv-transfer.md
docs/fern/kubernetes/topology-aware-scheduling.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/multinode/topology-aware-scheduling.md
docs/fern/kubernetes/vanilla-vllm-onramp.mdx	docs/fern/pages/kubernetes/kv-aware-routing/vanilla-vllm-onramp.mdx
docs/fern/kubernetes/webhooks.md	docs/fern/pages/developer-guide/knowledge-base/kubernetes/kubernetes-operator/webhooks.md
docs/fern/observability/README.md	docs/fern/pages/kubernetes/installation/observability.md
docs/fern/observability/local-observability.mdx	docs/fern/pages/cli/operations/observability.mdx
docs/fern/observability/local-resource-monitor.md	docs/fern/pages/reference/observability/local-resource-monitor-guide.md
docs/fern/observability/metrics-comparison.md	docs/fern/pages/reference/observability/metrics-comparison.md
docs/fern/observability/metrics-developer-guide.md	docs/fern/pages/developer-guide/advanced-customizations/metrics-developer-guide.md
docs/fern/performance/tuning.md	docs/fern/pages/kubernetes/operations/performance-tuning.md
docs/fern/proposals/vllm-rfc-forward-pass-metrics.md	docs/fern/pages/developer-guide/knowledge-base/concepts/observability/forward-pass-metrics-rfc.md
docs/fern/reasoning/README.md	docs/fern/pages/use-cases/tool-calling-and-reasoning/reasoning-parsing.md
docs/fern/recipes/README.mdx	docs/fern/pages/recipes/model-recipes/overview.mdx
docs/fern/recipes/deepseek-v3-2-nvfp4.mdx	docs/fern/pages/recipes/model-recipes/deepseek-v3-2-nvfp4.mdx
docs/fern/recipes/deepseek-v4-flash.mdx	docs/fern/pages/recipes/model-recipes/deepseek-v4-flash.mdx
docs/fern/recipes/deepseek-v4-pro.mdx	docs/fern/pages/recipes/model-recipes/deepseek-v4-pro.mdx
docs/fern/recipes/glm-5-2.mdx	docs/fern/pages/recipes/model-recipes/glm-5-2.mdx
docs/fern/recipes/glm-5-nvfp4.mdx	docs/fern/pages/recipes/model-recipes/glm-5-nvfp4.mdx
docs/fern/recipes/gpt-oss-120b.mdx	docs/fern/pages/recipes/model-recipes/gpt-oss-120b.mdx
docs/fern/recipes/inkling.mdx	docs/fern/pages/recipes/model-recipes/inkling-nvfp4.mdx
docs/fern/recipes/kimi-k2-6.mdx	docs/fern/pages/recipes/model-recipes/kimi-k2-6.mdx
docs/fern/recipes/kimi-k3.mdx	docs/fern/pages/recipes/model-recipes/kimi-k3.mdx
docs/fern/recipes/llama-3-3-70b.mdx	docs/fern/pages/recipes/model-recipes/llama-3-3-70b-fp8.mdx
docs/fern/recipes/nemotron-3-super.mdx	docs/fern/pages/recipes/model-recipes/nemotron-3-super.mdx
docs/fern/recipes/nemotron-3-ultra.mdx	docs/fern/pages/recipes/model-recipes/nemotron-3-ultra.mdx
docs/fern/recipes/qwen3-235b-a22b-fp8.mdx	docs/fern/pages/recipes/model-recipes/qwen3-235b-a22b-fp8.mdx
docs/fern/recipes/qwen3-32b-fp8.mdx	docs/fern/pages/recipes/model-recipes/qwen3-32b-fp8.mdx
docs/fern/recipes/qwen3-32b.mdx	docs/fern/pages/recipes/model-recipes/qwen3-32b.mdx
docs/fern/reference/agents/thunderagent-scheduler.mdx	docs/fern/pages/reference/components/thunderagent-scheduler.mdx
docs/fern/reference/compatibility.mdx	docs/fern/pages/reference/general/compatibility.mdx
docs/fern/reference/deprecations.mdx	docs/fern/pages/reference/general/releases/deprecations.mdx
docs/fern/reference/examples.md	docs/fern/pages/reference/general/examples.md
docs/fern/reference/glossary.md	docs/fern/pages/reference/general/glossary.md
docs/fern/reference/known-issues.mdx	docs/fern/pages/reference/general/releases/known-issues.mdx
docs/fern/reference/model-early-access-builds.mdx	docs/fern/pages/reference/general/model-early-access-builds.mdx
docs/fern/reference/observability/environment-variables.mdx	docs/fern/pages/reference/observability/environment-variables.mdx
docs/fern/reference/observability/forward-pass-metrics-tracing.mdx	docs/fern/pages/reference/observability/forward-pass-metrics-traces.mdx
docs/fern/reference/observability/health-checks.mdx	docs/fern/pages/reference/observability/health-checks.mdx
docs/fern/reference/observability/local-resource-monitor.mdx	docs/fern/pages/reference/observability/local-resource-monitor-local.mdx
docs/fern/reference/observability/local-stack.mdx	docs/fern/pages/reference/observability/local-stack.mdx
docs/fern/reference/observability/logging.mdx	docs/fern/pages/reference/observability/logging.mdx
docs/fern/reference/observability/metric-labels.mdx	docs/fern/pages/reference/observability/metric-labels.mdx
docs/fern/reference/observability/metrics-catalog.mdx	docs/fern/pages/reference/observability/metrics-catalog.mdx
docs/fern/reference/observability/operator-metrics.mdx	docs/fern/pages/reference/observability/operator-metrics.mdx
docs/fern/reference/observability/request-tracing.mdx	docs/fern/pages/reference/observability/request-traces.mdx
docs/fern/reference/release-artifacts.mdx	docs/fern/pages/reference/general/release-artifacts.mdx
docs/fern/reference/release-notes/README.mdx	docs/fern/pages/reference/general/releases/release-history.mdx
docs/fern/reference/release-notes/v1-0-0.mdx	docs/fern/pages/reference/general/releases/dynamo-v1-0-0.mdx
docs/fern/reference/release-notes/v1-1-0.mdx	docs/fern/pages/reference/general/releases/dynamo-v1-1-0.mdx
docs/fern/reference/release-notes/v1-2-0.mdx	docs/fern/pages/reference/general/releases/dynamo-v1-2-0.mdx
docs/fern/reference/release-notes/v1-3-0.mdx	docs/fern/pages/reference/general/releases/dynamo-v1-3-0.mdx
docs/fern/reference/releases-data.mdx	docs/fern/pages/reference/general/releases-machine-readable.mdx
docs/fern/reference/runtime-config-reference.mdx	docs/fern/pages/reference/components/runtime-configuration.mdx
docs/fern/templates/dgdr.mdx	docs/fern/pages/recipes/kubernetes-templates/dgdr.mdx
docs/fern/templates/sglang.mdx	docs/fern/pages/recipes/kubernetes-templates/dgd/sglang.mdx
docs/fern/templates/trtllm.mdx	docs/fern/pages/recipes/kubernetes-templates/dgd/tensorrt-llm.mdx
docs/fern/templates/vllm.mdx	docs/fern/pages/recipes/kubernetes-templates/dgd/vllm.mdx
docs/fern/tool-calling/README.mdx	docs/fern/pages/use-cases/tool-calling-and-reasoning/tool-call-parsing.mdx
docs/fern/tool-calling/chat-processors.mdx	docs/fern/pages/use-cases/tool-calling-and-reasoning/chat-processors.mdx
docs/fern/tool-calling/introduction.mdx	docs/fern/pages/use-cases/tool-calling-and-reasoning/overview.mdx
docs/fern/tool-calling/structural-tag.md	docs/fern/pages/use-cases/tool-calling-and-reasoning/structural-tag.md
docs/fern/tool-calling/troubleshooting.md	docs/fern/pages/use-cases/tool-calling-and-reasoning/troubleshooting-tool-calls.md
docs/fern/tools/aiperf.mdx	docs/fern/pages/kubernetes/operations/benchmarking-with-aiperf.mdx
docs/fern/translations/zh-CN/pages/components/kvbm/README.md	docs/fern/translations/zh-CN/pages/developer-guide/knowledge-base/modular-components/kvbm/overview.md
docs/fern/translations/zh-CN/pages/components/planner/planner-guide.md	docs/fern/translations/zh-CN/pages/developer-guide/knowledge-base/modular-components/planner/planner-guide.md
docs/fern/translations/zh-CN/pages/components/router/README.md	docs/fern/translations/zh-CN/pages/developer-guide/knowledge-base/modular-components/router/overview.md
docs/fern/translations/zh-CN/pages/contribution-guide.md	docs/fern/translations/zh-CN/pages/community/contributing/overview.md
docs/fern/translations/zh-CN/pages/design-docs/architecture.md	docs/fern/translations/zh-CN/pages/developer-guide/knowledge-base/overview.md
docs/fern/translations/zh-CN/pages/design-docs/disagg-serving.md	docs/fern/translations/zh-CN/pages/developer-guide/knowledge-base/concepts/system-architecture/disaggregated-serving.md
docs/fern/translations/zh-CN/pages/design-docs/planner-design.md	docs/fern/translations/zh-CN/pages/developer-guide/knowledge-base/modular-components/planner/planner-design.md
docs/fern/translations/zh-CN/pages/fault-tolerance/request-migration.md	docs/fern/translations/zh-CN/pages/kubernetes/fault-tolerance/request-migration.md
docs/fern/translations/zh-CN/pages/getting-started/building-from-source.md	docs/fern/translations/zh-CN/pages/developer-guide/advanced-customizations/building-from-source.md
docs/fern/translations/zh-CN/pages/getting-started/introduction.mdx	docs/fern/translations/zh-CN/pages/kubernetes/getting-started/introduction.mdx
docs/fern/translations/zh-CN/pages/getting-started/local-installation.mdx	docs/fern/translations/zh-CN/pages/cli/installation/install-dynamo.mdx
docs/fern/translations/zh-CN/pages/getting-started/quickstart.mdx	docs/fern/translations/zh-CN/pages/cli/getting-started/quickstart.mdx
docs/fern/translations/zh-CN/pages/tool-calling/README.mdx	docs/fern/translations/zh-CN/pages/use-cases/tool-calling-and-reasoning/tool-call-parsing.mdx
docs/fern/welcome.mdx	docs/fern/pages/home/index.mdx

@copy-pr-bot

copy-pr-bot Bot commented Jul 29, 2026

Copy link
Copy Markdown

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@Jont828
Jont828 requested review from a team as code owners July 29, 2026 18:08
@Jont828
Jont828 temporarily deployed to external_collaborator July 29, 2026 18:08 — with GitHub Actions Inactive
@Jont828
Jont828 temporarily deployed to external_collaborator July 29, 2026 18:08 — with GitHub Actions Inactive
@github-actions github-actions Bot added external-contribution Pull request is from an external contributor trusted-contributor Org-External user who is trusted to run CI without Org-member approval labels Jul 29, 2026
@dynamo-ops

Copy link
Copy Markdown
Contributor

/ok to test 6fb4efb

@github-actions github-actions Bot added docs documentation Improvements or additions to documentation backend::vllm Relates to the vllm backend deployment::k8s Relates to dynamo deployment in kubernetes labels Jul 29, 2026
@Jont828
Jont828 temporarily deployed to external_collaborator July 30, 2026 23:15 — with GitHub Actions Inactive
@dynamo-ops

Copy link
Copy Markdown
Contributor

/ok to test 420bf2e

@Jont828
Jont828 temporarily deployed to external_collaborator July 30, 2026 23:37 — with GitHub Actions Inactive
@dynamo-ops

Copy link
Copy Markdown
Contributor

/ok to test 4c960c1

@Jont828
Jont828 force-pushed the docs-folder-restructure branch from 4c960c1 to 404a05c Compare July 30, 2026 23:51
@Jont828
Jont828 temporarily deployed to external_collaborator July 30, 2026 23:51 — with GitHub Actions Inactive
@dynamo-ops

Copy link
Copy Markdown
Contributor

/ok to test 404a05c

Signed-off-by: Jont828 <jt572@cornell.edu>
@Jont828
Jont828 force-pushed the docs-folder-restructure branch from 404a05c to 51933c2 Compare July 31, 2026 00:07
@Jont828
Jont828 temporarily deployed to external_collaborator July 31, 2026 00:07 — with GitHub Actions Inactive
@dynamo-ops

Copy link
Copy Markdown
Contributor

/ok to test 51933c2

@Jont828

Jont828 commented Jul 31, 2026

Copy link
Copy Markdown
Contributor Author

Docs link check was b/c of a change to Helm chart, can do that as follow up bc it requires approval from gms owners

@dagil-nvidia
dagil-nvidia merged commit a0245de into ai-dynamo:main Jul 31, 2026
101 of 104 checks passed
Change72 added a commit to Change72/dynamo that referenced this pull request Jul 31, 2026
ai-dynamo#12373 moved docs/fern/kubernetes/snapshot.md to
docs/fern/pages/developer-guide/knowledge-base/kubernetes/kubernetes-operator/snapshot.md
but left the link in the snapshot Helm chart README pointing at the old
path, which the docs link check flags as broken. Point it at the new
location.

Signed-off-by: Change72 <changg@nvidia.com>
dagil-nvidia added a commit that referenced this pull request Jul 31, 2026
Three shared-ownership globs referenced paths that were moved (not
deleted) by a0245de ("docs: align documentation paths with site
structure", #12373). This PR's new hardened strict gate treats stale
globs as blocking, so those three now fail the coverage/policy gate
against current main.

Pruning them would silently drop docs, agents, and backend-sglang
co-ownership from content that is still live, which is exactly the
accountability loss .github/codeowners/README.md warns against.
Re-point each glob at its current path instead, preserving team
assignments:

- docs/fern/agents/                       -> docs/fern/pages/use-cases/agents/
- docs/fern/backends/sglang/agents.md     -> docs/fern/pages/developer-guide/knowledge-base/modular-components/backends/sglang/agents-on-sglang.md
- docs/fern/digest/agentic-inference/     -> docs/fern/pages/blog/2026/agentic-harness-support.mdx
                                             docs/fern/pages/blog/2026/agentic-inference-optimizations.mdx

The digest folder fans out: assign docs+agents co-ownership only to
the two article files, not the sibling _assets/agentic-inference/
tree, since binary/asset files do not need docs+agents review.

Regenerated CODEOWNERS via emit_codeowners.py; the base+shared column
alignment shifts because the new sglang path is the longest glob, but
the -w diff shows only the four expected content changes.

Strict gate now exits 0. 137 codeowners tests pass. Coverage 100%.

Signed-off-by: Dan Gil <dagil@nvidia.com>
dagil-nvidia added a commit that referenced this pull request Aug 1, 2026
[kv-routing] and [mm-vllm] have no remaining references on the page -- the
multimodal citations moved to [mm-kv-routing] and the KV-routing citation
went with the accordion. Both were kept by mistake when resolving the
rebase against the #12373 path rename, which carried HEAD's full definition
list rather than the narrower set this commit intends.

Signed-off-by: Dan Gil <dagil@nvidia.com>
dagil-nvidia added a commit that referenced this pull request Aug 1, 2026
…ave it

The support-matrix accordion told readers that the notes below it cover the
toolkit support of every platform preview and model-specific build the matrix
excludes. They do not. CUDA_NOTES names v1.1.0-dev.* and
v1.2.0-deepseek-v4-dev.3; RELEASES also carries v1.3.0-dev.1 and
v1.2.0-deepseek-v4-dev.2, and neither has a note or a CUDA_HISTORY row. A
reader on one of those two was sent to information that is not there.

No CUDA version is recorded for either build anywhere in the repo -- not in
releases.data.ts, not in model-early-access-builds, not in the generated
inventory -- so documenting them would mean inventing toolkit requirements
rather than reporting them. The caption is narrowed instead: it now promises
coverage for the builds a note actually names and continues to point at the
machine-readable inventory for the rest. The comment on SUPPORT_MATRIX_KINDS
records which builds are uncovered and why the wording is hedged, so the next
person to add a note knows what the gap is.

Validation: gen_llms_tables.py --check reports all seven outputs unchanged
after regeneration (compatibility.mdx is the only one that moved, by the one
caption sentence). fern check is 0 errors / 1292 warnings, the baseline.
check_reference.sh gates 1, 2, 3 and 5 pass, including fern broken-links at 0
site errors; gate 4 raises StopIteration on main as well, from #12373 removing
the nav variants layer, and is untouched here.

Signed-off-by: Dan Gil <dagil@nvidia.com>
dagil-nvidia added a commit that referenced this pull request Aug 2, 2026
Relocates the Proposals tab onto main's post-restructure docs layout (#10855
fern/ -> docs/fern/, #12373 page renames):

- docs/proposals/*.mdx        -> docs/fern/pages/proposals/*.mdx
- fern/components/Dep*.tsx    -> docs/fern/components/
- fern/js/dep-*.js            -> docs/fern/js/
- fern/scripts/sync_deps.py   -> docs/fern/scripts/
- fern/docs.yml js: entries   -> docs/fern/docs.yml
- docs/index.yml proposals tab-> docs/fern/index.yml
- docs/fern/main.css: kept both sides (main's Community/Mermaid blocks and
  the DEP status-pill block)

Path constants, fixtures, workflow steps and .gitignore follow the move.
The generated dir is now docs/fern/pages/proposals/_generated/, which sits
under docs/fern/pages/ so the docs-website rsync picks it up.

Signed-off-by: Dan Gil <dagil@nvidia.com>
dagil-nvidia added a commit that referenced this pull request Aug 3, 2026
The Reference tab's General group is shared across versions: release
snapshots keep its nav on ../pages-dev/ so every version dropdown renders
the always-current reference. Both the workflow and the composition
harness found that group with

  .navigation[] | select(.tab == "reference")
    | .variants[] | select(.title == "General")

#12410 deliberately flattened the Reference tab into folded sections with
no variant selector. The selector has matched nothing since 2026-07-30 --
verified against docs-website, where dev.yml carried `title: General` on
07-27 through 07-29 and lost it on 07-30. Shared Reference has been off
ever since, and would have frozen a per-version reference copy at the next
tag cut. Nothing failed, because the only guard was a ::warning:: that
fires during a tag cut where nobody reads it.

Key the group on where its content lives instead. #12373 moved those pages
to pages/reference/general/ and gave every other former variant its own
directory, so the split the variants expressed in the nav is now expressed
by directory -- a signal IA work does not rename in passing. The Reference
tab's flattening is preserved; only the machinery moves.

The snapshot drop and the version-config revert become plain path
operations, which also removes a live defect: a yq assignment whose
left-hand side traverses a missing key auto-creates it, so the dead
`.variants[]` selector injected an empty `variants: []` into the composed
dev.yml and <TAG>.yml. That invalidates the whole navigation against
Fern's schema -- reported confusingly as a bad object at
$.navigation[4].layout[3], several hundred lines from the injection.
That is the Docs Website Composition Check failure on this PR, and the
same unguarded assignment in the release-version job would have corrupted
the next tag's version file.

Both silent-skip paths in the workflow become hard failures, and the
harness gains assertion 9 asserting the group is findable at all, so the
next rename fails on the PR that causes it rather than six days later.
Assertion 4 also stops false-passing: its find target no longer exists, so
find errored and wc counted zero while the assertion reported ok.

Validation:
  DOCS_WEBSITE_REF=origin/docs-website \
    bash docs/fern/scripts/simulate_docs_website.sh

  9. dev.yml exposes a shared Reference group (7 entries)          ok
  2. v9.9.9.yml: reference/general shared (13 pages-dev refs)      ok
  2. v9.9.9.yml: Components section frozen (runtime configuration) ok
  3. snapshot drops shared files, keeps versioned reference/       ok
  5. pre-rework versions gain no shared-reference pointers         ok
  6. round-two propagation reaches the cut version's nav           ok
  7. converter moved to fern/scripts/ with no stale root copy      ok
  8. translated links resolve to dev and tag-pinned site URLs      ok
  1. fern check on composed tree (0 errors)                        ok
  ALL ASSERTIONS PASSED

Was four FAILs (2, 3, 6 and fern check) before this change. Negative test:
renaming pages/reference/general/ to reference/core/ fails assertion 9 with
exit 1 while fern check stays at 0 errors, confirming a non-matching
selector no longer corrupts the tree. Composed dev.yml and v9.9.9.yml carry
no variants key. bash -n passes on all 33 run blocks in fern-docs.yml.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Signed-off-by: Dan Gil <dagil@nvidia.com>
jh-nv added a commit that referenced this pull request Aug 12, 2026
The launch script this entry links to is added by this PR, so the
blob/main URL 404s until the PR merges and lychee fails on it. The
repository already sequences these separately: agg_embed.sh landed in
#9713 and its examples-page entry followed in #12373 once the file
existed on main.

Reverts only the docs hunk; the pooling rank validation stays.

Signed-off-by: Jie Hao <jihao@nvidia.com>
jh-nv added a commit that referenced this pull request Aug 12, 2026
The launch script this entry links to is added by this PR, so the
blob/main URL 404s until the PR merges and lychee fails on it. The
repository already sequences these separately: agg_embed.sh landed in
#9713 and its examples-page entry followed in #12373 once the file
existed on main.

Reverts only the docs hunk; the pooling rank validation stays.

Signed-off-by: Jie Hao <jihao@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

actions backend::sglang Relates to the sglang backend backend::trtllm Relates to the trtllm backend backend::vllm Relates to the vllm backend deployment::k8s Relates to dynamo deployment in kubernetes docs documentation Improvements or additions to documentation external-contribution Pull request is from an external contributor frontend `python -m dynamo.frontend` and `dynamo-run in=http|text|grpc` planner router Relates to routing, KV-aware routing, etc. trusted-contributor Org-External user who is trusted to run CI without Org-member approval xpu

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants