Use HuggingFace model names and full NVCR container paths

yeswanthk-26 · yeswanthk-26 · commit 502d7465cd55 · 2026-04-10T05:28:46.000Z
Per review feedback, update model paths to HuggingFace format
(nvidia/Kimi-K2.5-NVFP4) and container to full NVCR registry path
(nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2) so recipes
are portable and work without pre-built sqsh files.
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx1dep4_gen1dep16_batch32_eplb0_mtp3.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx1dep4_gen1dep16_batch32_eplb0_mtp3.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx1dep4_gen1dep16_batch32_eplb0_mtp3"
 # concurrency: 666
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -115,7 +115,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx1dep4_gen1dep32_batch16_eplb0_mtp3.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx1dep4_gen1dep32_batch16_eplb0_mtp3.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx1dep4_gen1dep32_batch16_eplb0_mtp3"
 # concurrency: 666
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -113,7 +113,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx1dep4_gen1dep8_batch512_eplb0_mtp1.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx1dep4_gen1dep8_batch512_eplb0_mtp1.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx1dep4_gen1dep8_batch512_eplb0_mtp1"
 # concurrency: 4301
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -175,7 +175,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx1dep4_gen4tep8_batch64_allconc_eplb0_mtp3.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx1dep4_gen4tep8_batch64_allconc_eplb0_mtp3.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx1dep4_gen4tep8_batch64_allconc_eplb0_mtp3"
 # Covers all gen4tep8 concurrencies: 8, 48, 92, 192, 336
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -120,7 +120,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx1dep4_gen5tep4_batch2_allconc_eplb0_mtp3.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx1dep4_gen5tep4_batch2_allconc_eplb0_mtp3.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx1dep4_gen5tep4_batch2_allconc_eplb0_mtp3"
 # Covers all gen5tep4 concurrencies: 10, 15
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -111,7 +111,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx2dep4_gen1dep16_batch128_eplb0_mtp1.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx2dep4_gen1dep16_batch128_eplb0_mtp1.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx2dep4_gen1dep16_batch128_eplb0_mtp1"
 # concurrency: 2253
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -127,7 +127,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx2dep4_gen1dep32_batch64_eplb0_mtp1.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx2dep4_gen1dep32_batch64_eplb0_mtp1.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx2dep4_gen1dep32_batch64_eplb0_mtp1"
 # concurrency: 2253
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -119,7 +119,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx2dep4_gen3dep8_batch256_eplb0_mtp1.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/MTP/ctx2dep4_gen3dep8_batch256_eplb0_mtp1.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx2dep4_gen3dep8_batch256_eplb0_mtp1"
 # concurrency: 6759
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -143,7 +143,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx1dep4_gen1dep16_batch32_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx1dep4_gen1dep16_batch32_eplb0_mtp0.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx1dep4_gen1dep16_batch32_eplb0_mtp0"
 # concurrency: 666
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx1dep4_gen1dep32_batch64_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx1dep4_gen1dep32_batch64_eplb0_mtp0.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx1dep4_gen1dep32_batch64_eplb0_mtp0"
 # concurrency: 2253
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx1dep4_gen1dep8_batch768_allconc_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx1dep4_gen1dep8_batch768_allconc_eplb0_mtp0.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx1dep4_gen1dep8_batch768_allconc_eplb0_mtp0"
 # Covers all dep8 concurrencies: 4301, 6452
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx1dep4_gen4tep8_batch128_allconc_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx1dep4_gen4tep8_batch128_allconc_eplb0_mtp0.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx1dep4_gen4tep8_batch128_allconc_eplb0_mtp0"
 # Covers all gen4tep8 concurrencies: 4, 192, 360, 668
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx1dep4_gen5tep4_batch8_allconc_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx1dep4_gen5tep4_batch8_allconc_eplb0_mtp0.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx1dep4_gen5tep4_batch8_allconc_eplb0_mtp0"
 # Covers all gen5tep4 concurrencies: 5, 15, 30, 55
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx2dep4_gen1dep16_batch256_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx2dep4_gen1dep16_batch256_eplb0_mtp0.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx2dep4_gen1dep16_batch256_eplb0_mtp0"
 # concurrency: 4301
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx2dep4_gen1dep32_batch128_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL1K_OSL1K/STP/ctx2dep4_gen1dep32_batch128_eplb0_mtp0.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL1K_OSL1K_ctx2dep4_gen1dep32_batch128_eplb0_mtp0"
 # concurrency: 4301
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx1dep4_gen2tep8_batch32_eplb0_mtp3.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx1dep4_gen2tep8_batch32_eplb0_mtp3.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL8K_OSL1K_ctx1dep4_gen2tep8_batch32_eplb0_mtp3"
 # concurrency: 90
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -116,7 +116,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx1dep4_gen4tep8_batch1_eplb0_mtp3.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx1dep4_gen4tep8_batch1_eplb0_mtp3.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL8K_OSL1K_ctx1dep4_gen4tep8_batch1_eplb0_mtp3"
 # concurrency: 8
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -112,7 +112,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx1dep4_gen5tep4_batch8_allconc_eplb0_mtp3.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx1dep4_gen5tep4_batch8_allconc_eplb0_mtp3.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL8K_OSL1K_ctx1dep4_gen5tep4_batch8_allconc_eplb0_mtp3"
 # Covers all gen5tep4 concurrencies: 10, 15, 60
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -112,7 +112,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx2dep4_gen1dep16_batch8_eplb0_mtp3.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx2dep4_gen1dep16_batch8_eplb0_mtp3.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL8K_OSL1K_ctx2dep4_gen1dep16_batch8_eplb0_mtp3"
 # concurrency: 180
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -112,7 +112,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx5dep4_gen1dep32_batch16_eplb0_mtp3.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx5dep4_gen1dep32_batch16_eplb0_mtp3.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL8K_OSL1K_ctx5dep4_gen1dep32_batch16_eplb0_mtp3"
 # concurrency: 666
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -113,7 +113,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx5dep4_gen1dep8_batch256_allconc_eplb0_mtp1.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx5dep4_gen1dep8_batch256_allconc_eplb0_mtp1.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL8K_OSL1K_ctx5dep4_gen1dep8_batch256_allconc_eplb0_mtp1"
 # Covers all dep8 mtp1 concurrencies: 1229, 2253
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -143,7 +143,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx8dep4_gen1dep32_batch32_eplb0_mtp3.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/MTP/ctx8dep4_gen1dep32_batch32_eplb0_mtp3.yaml
@@ -6,8 +6,8 @@ name: "kimi_k25_nvfp4_ISL8K_OSL1K_ctx8dep4_gen1dep32_batch32_eplb0_mtp3"
 # concurrency: 1229
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
@@ -115,7 +115,7 @@ backend:
         speculative_model_dir: "/eagle-model"
 
 extra_mount:
-  - "kimi-k2.5-eagle3:/eagle-model"
+  - "nvidia/Kimi-K2.5-Thinking-Eagle3:/eagle-model"
 
 benchmark:
   type: "sa-bench"
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx1dep4_gen4tep4_batch32_allconc_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx1dep4_gen4tep4_batch32_allconc_eplb0_mtp0.yaml
@@ -5,8 +5,8 @@ name: "kimi_k25_nvfp4_ISL8K_OSL1K_ctx1dep4_gen4tep4_batch32_allconc_eplb0_mtp0"
 # Single concurrency point: 156
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx1dep4_gen4tep8_batch1_allconc_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx1dep4_gen4tep8_batch1_allconc_eplb0_mtp0.yaml
@@ -5,8 +5,8 @@ name: "kimi_k25_nvfp4_ISL8K_OSL1K_ctx1dep4_gen4tep8_batch1_allconc_eplb0_mtp0"
 # Single concurrency point: 4
 
 model:
-  path: "kimi-k2.5-nvfp4"
-  container: "tensorrtllm-runtime:1.1.0-dev.2"
+  path: "nvidia/Kimi-K2.5-NVFP4"
+  container: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.1.0-dev.2"
   precision: "fp4"
 
 resources:
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx1dep4_gen5tep4_batch16_allconc_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx1dep4_gen5tep4_batch16_allconc_eplb0_mtp0.yaml
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx2dep4_gen1dep16_batch16_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx2dep4_gen1dep16_batch16_eplb0_mtp0.yaml
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx3dep4_gen1dep16_batch32_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx3dep4_gen1dep16_batch32_eplb0_mtp0.yaml
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx5dep4_gen1dep8_batch256_allconc_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx5dep4_gen1dep8_batch256_allconc_eplb0_mtp0.yaml
diff --git a/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx7dep4_gen1dep16_batch128_eplb0_mtp0.yaml b/recipes/kimi2.5/trtllm_dynamo/disagg/gb200Nvfp4/ISL8K_OSL1K/STP/ctx7dep4_gen1dep16_batch128_eplb0_mtp0.yaml
