[Klaud Cold] Update dsr1-fp8-b200-trt (+mtp) TRT-LLM image to v1.3.0rc14 (#1488)

* Update dsr1-fp8-b200-trt (+mtp) TRT-LLM image to v1.3.0rc14

Update TensorRT-LLM image (off: v1.2.0rc6.post2 109d / mtp: v1.2.0rc6.post3 102d) to v1.3.0rc14 (latest pre-release)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: fill pr-link for #1488

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: functionstackx

.github/configs/nvidia-master.yaml

@@ -2776,7 +2776,7 @@ kimik2.5-fp4-b300-vllm-agentic:
       - { tp: 8, ep: 1, offloading: cpu,  conc-list: [1, 2, 4, 8, 16, 32, 40, 48, 56, 64] }
 
 dsr1-fp8-b200-trt:
-  image: nvcr.io#nvidia/tensorrt-llm/release:1.2.0rc6.post2
+  image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: b200
@@ -2799,7 +2799,7 @@ dsr1-fp8-b200-trt:
       - { tp: 8, ep: 1, conc-start: 4, conc-end: 8 }
 
 dsr1-fp8-b200-trt-mtp:
-  image: nvcr.io#nvidia/tensorrt-llm/release:1.2.0rc6.post3
+  image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: b200

perf-changelog.yaml

@@ -2755,3 +2755,10 @@
     - "Update SGLang image from v0.5.11-cu130 to v0.5.12-cu130"
     - "Disable JIT DeepGemm (SGL_ENABLE_JIT_DEEPGEMM=0) to bypass v0.5.12 DeepGemm TMA-descriptor regression on B300 — see sgl-project/sglang#25551"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1421
+
+- config-keys:
+    - dsr1-fp8-b200-trt
+    - dsr1-fp8-b200-trt-mtp
+  description:
+    - "Update TensorRT-LLM image (off: v1.2.0rc6.post2 109d / mtp: v1.2.0rc6.post3 102d) to v1.3.0rc14 (latest pre-release)"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1488