Switch B300 DSv4 TRT image to nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.3.0-deepseek-v4-dev.1

Update both dsv4-fp4-b300-trt and dsv4-fp4-b300-trt-mtp to the Dynamo
TensorRT-LLM runtime image. Also removes stale perf-changelog entry
that contradicted the launcher behavior.

Co-authored-by: functionstackx <functionstackx@users.noreply.github.com>

Author: github-actions[bot]

.github/configs/nvidia-master.yaml

@@ -3049,7 +3049,7 @@ dsv4-fp4-b300-vllm-agentic:
       - { tp: 8, ep: 8, dp-attn: true, offloading: cpu,  conc-list: [128, 256, 512] }
 
 dsv4-fp4-b300-trt:
-  image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc15.post1
+  image: nvcr.io#nvidia/ai-dynamo/tensorrtllm-runtime:1.3.0-deepseek-v4-dev.1
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: b300
@@ -3072,7 +3072,7 @@ dsv4-fp4-b300-trt:
       - { tp: 8, ep: 8, dp-attn: true, conc-start: 256, conc-end: 1024 }
 
 dsv4-fp4-b300-trt-mtp:
-  image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc15.post1
+  image: nvcr.io#nvidia/ai-dynamo/tensorrtllm-runtime:1.3.0-deepseek-v4-dev.1
   model: deepseek-ai/DeepSeek-V4-Pro
   model-prefix: dsv4
   runner: b300

perf-changelog.yaml

@@ -3387,13 +3387,6 @@
     - "Add MTP speculative-decoding sibling for dsv4-fp4-mi355x-vllm (model: deepseek-ai/DeepSeek-V4-Pro) on vllm/vllm-openai-rocm:v0.22.0, per vllm-project/vllm#43385"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1630
 
-- config-keys:
-    - dsv4-fp4-b300-trt
-    - dsv4-fp4-b300-trt-mtp
-  description:
-    - "Point the B300 TensorRT-LLM DeepSeek-V4-Pro configs (non-MTP dsv4-fp4-b300-trt and MTP dsv4-fp4-b300-trt-mtp) at the official NVIDIA release image nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc15.post1, replacing the custom ghcr.io semianalysis feat/deepseek_v4 builds (2dd03e6 and 9aa3715 respectively), to evaluate the official RC for DeepSeek-V4-Pro. Also drops the TRTLLM_DSV4_ENABLE_SWA_SCRATCH_REUSE=0 launcher workaround (specific to the custom build) so the official image runs with its native behavior. B200 TRT is unchanged (stays on feat-deepseek_v4-9aa3715)."
-  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1636
-
 - config-keys:
     - dsv4-fp4-mi355x-sglang-mtp
   description:
@@ -3516,3 +3509,10 @@
     - "Update GPT-OSS model for MI355X vLLM from amd/gpt-oss-120b-w-mxfp4-a-fp8 to openai/gpt-oss-120b"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1670
 
+- config-keys:
+    - dsv4-fp4-b300-trt
+    - dsv4-fp4-b300-trt-mtp
+  description:
+    - "Switch B300 DSv4 TRT (non-MTP + MTP) image from rc15.post1 to nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.3.0-deepseek-v4-dev.1"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1636
+