chore: import upstream snapshot with attribution

doc/source/serve/doc_code/pd_dissagregation/lmcache/mooncake.yaml

@@ -0,0 +1,17 @@
+# LMCache configuration for Mooncake store backend
+chunk_size: 256
+local_device: "cpu"
+remote_url: "mooncakestore://storage-server:49999/"
+remote_serde: "naive"
+pipelined_backend: false
+local_cpu: false
+max_local_cpu_size: 5
+extra_config:
+  local_hostname: "compute-node-001"
+  metadata_server: "etcd://metadata-server:2379"
+  protocol: "rdma"
+  device_name: "rdma0"
+  master_server_address: "storage-server:49999"
+  global_segment_size: 3355443200  # 3.125 GB
+  local_buffer_size: 1073741824    # 1 GB
+  transfer_timeout: 1

doc/source/serve/doc_code/pd_dissagregation/lmcache/nixl/decoder.yaml

@@ -0,0 +1,12 @@
+local_cpu: False
+max_local_cpu_size: 0
+max_local_disk_size: 0
+remote_serde: NULL
+
+enable_nixl: True
+nixl_role: "receiver"
+nixl_receiver_host: "localhost"
+nixl_receiver_port: 55555
+nixl_buffer_size: 1073741824 # 1GB
+nixl_buffer_device: "cuda"
+nixl_enable_gc: True

doc/source/serve/doc_code/pd_dissagregation/lmcache/nixl/prefiller.yaml

@@ -0,0 +1,12 @@
+local_cpu: False
+max_local_cpu_size: 0
+max_local_disk_size: 0
+remote_serde: NULL
+
+enable_nixl: True
+nixl_role: "sender"
+nixl_receiver_host: "localhost"
+nixl_receiver_port: 55555
+nixl_buffer_size: 1073741824 # 1GB
+nixl_buffer_device: "cuda"
+nixl_enable_gc: True

doc/source/serve/doc_code/pd_dissagregation/lmcache_mooncake_example.yaml

@@ -0,0 +1,34 @@
+# Example: LMCacheConnectorV1 with Mooncake store configuration
+
+applications:
+  - args:
+      prefill_config:
+        model_loading_config:
+          model_id: meta-llama/Llama-3.1-8B-Instruct
+        engine_kwargs:
+          kv_transfer_config: &kv_transfer_config
+            kv_connector: LMCacheConnectorV1
+            kv_role: kv_both
+        deployment_config:
+          autoscaling_config:
+            min_replicas: 2
+            max_replicas: 2
+        runtime_env: &runtime_env
+          env_vars:
+            LMCACHE_CONFIG_FILE: lmcache_mooncake.yaml
+            LMCACHE_USE_EXPERIMENTAL: "True"
+
+      decode_config:
+        model_loading_config:
+          model_id: meta-llama/Llama-3.1-8B-Instruct
+        engine_kwargs:
+          kv_transfer_config: *kv_transfer_config
+        deployment_config:
+          autoscaling_config:
+            min_replicas: 1
+            max_replicas: 1
+        runtime_env: *runtime_env
+
+    import_path: ray.serve.llm:build_pd_openai_app
+    name: pd-disaggregation-lmcache-mooncake
+    route_prefix: "/"

doc/source/serve/doc_code/pd_dissagregation/lmcache_nixl_example.yaml

@@ -0,0 +1,45 @@
+# Example: LMCacheConnectorV1 with NIXL backend configuration
+
+applications:
+  - args:
+      prefill_config:
+        model_loading_config:
+          model_id: meta-llama/Llama-3.1-8B-Instruct
+        engine_kwargs:
+          kv_transfer_config:
+            kv_connector: LMCacheConnectorV1
+            kv_role: kv_producer
+            kv_connector_extra_config:
+              discard_partial_chunks: false
+              lmcache_rpc_port: producer1
+        deployment_config:
+          autoscaling_config:
+            min_replicas: 2
+            max_replicas: 2
+        runtime_env:
+          env_vars:
+            LMCACHE_CONFIG_FILE: lmcache_prefiller.yaml
+            LMCACHE_USE_EXPERIMENTAL: "True"
+
+      decode_config:
+        model_loading_config:
+          model_id: meta-llama/Llama-3.1-8B-Instruct
+        engine_kwargs:
+          kv_transfer_config:
+            kv_connector: LMCacheConnectorV1
+            kv_role: kv_consumer
+            kv_connector_extra_config:
+              discard_partial_chunks: false
+              lmcache_rpc_port: consumer1
+        deployment_config:
+          autoscaling_config:
+            min_replicas: 6
+            max_replicas: 6
+        runtime_env:
+          env_vars:
+            LMCACHE_CONFIG_FILE: lmcache_decoder.yaml
+            LMCACHE_USE_EXPERIMENTAL: "True"
+
+    import_path: ray.serve.llm:build_pd_openai_app
+    name: pd-disaggregation-lmcache-nixl
+    route_prefix: "/"

doc/source/serve/doc_code/pd_dissagregation/nixl_example.yaml

@@ -0,0 +1,34 @@
+# Example: Basic NIXLConnector configuration for prefill/decode disaggregation
+# nixl_config.yaml
+
+applications:
+  - args:
+      prefill_config:
+        model_loading_config:
+          model_id: meta-llama/Llama-3.1-8B-Instruct
+        engine_kwargs:
+          kv_transfer_config:
+            kv_connector: NixlConnector
+            kv_role: kv_producer
+            engine_id: engine1
+        deployment_config:
+          autoscaling_config:
+            min_replicas: 2
+            max_replicas: 4
+      
+      decode_config:
+        model_loading_config:
+          model_id: meta-llama/Llama-3.1-8B-Instruct
+        engine_kwargs:
+          kv_transfer_config:
+            kv_connector: NixlConnector
+            kv_role: kv_consumer
+            engine_id: engine2
+        deployment_config:
+          autoscaling_config:
+            min_replicas: 6
+            max_replicas: 10
+
+    import_path: ray.serve.llm:build_pd_openai_app
+    name: pd-disaggregation-nixl
+    route_prefix: "/"