docs: Clean up incomplete recipes and clarify Kubernetes-only focus (#4159)

Signed-off-by: Ben Hamm <ben.hamm@gmail.com>
Signed-off-by: Tanmay Verma <tanmay2592@gmail.com>
Signed-off-by: atchernych <atchernych@nvidia.com>
Co-authored-by: Biswa Panda <biswa.panda@gmail.com>
Co-authored-by: tanmayv25 <tanmay2592@gmail.com>
Co-authored-by: Tanmay Verma <tanmayv@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: atchernych <atchernych@nvidia.com>

recipes/deepseek-r1/trtllm/agg/wide_ep/wide_ep_agg.yaml → examples/backends/trtllm/engine_configs/deepseek-r1/agg/wide_ep/wide_ep_agg.yaml

@@ -11,7 +11,7 @@ moe_config:
   #   moe_max_num_tokens = max_batch_size * moe_expert_parallel_size
   #   4096 = 256 * 16
   # moe_max_num_tokens: 4096
-  load_balancer: /mnt/recipes/deepseek-r1/trtllm/agg/wide_ep/eplb.yaml
+  load_balancer: /mnt/examples/backends/trtllm/engine_configs/deepseek-r1/agg/wide_ep/eplb.yaml
 
 tensor_parallel_size: 16
 moe_expert_parallel_size: 16

recipes/deepseek-r1/trtllm/disagg/wide_ep/wide_ep_decode.yaml → examples/backends/trtllm/engine_configs/deepseek-r1/disagg/wide_ep/wide_ep_decode.yaml

@@ -17,7 +17,7 @@ backend: pytorch
 # WideEP related settings
 moe_config:
   backend: WIDEEP
-  load_balancer: /mnt/recipes/deepseek-r1/trtllm/disagg/wide_ep/eplb.yaml
+  load_balancer: /mnt/examples/backends/trtllm/engine_configs/deepseek-r1/disagg/wide_ep/eplb.yaml
 
 # TP/EP/PP/DP
 tensor_parallel_size: 16

recipes/deepseek-r1/trtllm/disagg/wide_ep/wide_ep_prefill.yaml → examples/backends/trtllm/engine_configs/deepseek-r1/disagg/wide_ep/wide_ep_prefill.yaml

@@ -17,7 +17,7 @@ backend: pytorch
 # WideEP related settings
 moe_config:
   backend: WIDEEP
-  load_balancer: /mnt/recipes/deepseek-r1/trtllm/disagg/wide_ep/eplb.yaml
+  load_balancer: /mnt/examples/backends/trtllm/engine_configs/deepseek-r1/disagg/wide_ep/eplb.yaml
 
 # TP/EP/PP/DP
 tensor_parallel_size: 16

examples/backends/trtllm/engine_configs/gpt-oss-120b/decode.yaml

+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+enable_attention_dp: true
+disable_overlap_scheduler: false
+moe_config:
+    backend: CUTLASS
+cuda_graph_config:
+    enable_padding: true
+cache_transceiver_config:
+  backend: UCX
+  max_tokens_in_buffer: 65536
+print_iter_log: false
+stream_interval: 10

examples/backends/trtllm/engine_configs/gpt-oss-120b/prefill.yaml

+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+enable_attention_dp: false
+disable_overlap_scheduler: true
+moe_config:
+    backend: CUTLASS
+enable_chunked_prefill: true
+cuda_graph_config:
+    max_batch_size: 32
+    enable_padding: true
+cache_transceiver_config:
+  backend: UCX
+  max_tokens_in_buffer: 65536
+print_iter_log: false
+stream_interval: 10