[Klaud Cold] Update dsr1-fp8-h200-trt (+mtp) TRT-LLM image to v1.3.0rc14 (#1487)

* Update dsr1-fp8-h200-trt (+mtp) TRT-LLM image to v1.3.0rc14

Update TensorRT-LLM image from v1.1.0rc2.post2 (154d/124d old) to v1.3.0rc14 (latest pre-release)

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

* chore: fill pr-link for #1487

---------

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

Author: functionstackx

.github/configs/nvidia-master.yaml

@@ -3160,7 +3160,7 @@ glm5-fp8-h200-sglang-mtp:
       - { tp: 8, conc-start: 4, conc-end: 64, spec-decoding: mtp }
 
 dsr1-fp8-h200-trt:
-  image: nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2
+  image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: h200
@@ -3183,7 +3183,7 @@ dsr1-fp8-h200-trt:
       - { tp: 8, ep: 8, dp-attn: true, conc-start: 64, conc-end: 64 }
 
 dsr1-fp8-h200-trt-mtp:
-  image: nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2
+  image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14
   model: deepseek-ai/DeepSeek-R1-0528
   model-prefix: dsr1
   runner: h200

perf-changelog.yaml

@@ -2762,3 +2762,10 @@
   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
+
+- config-keys:
+    - dsr1-fp8-h200-trt
+    - dsr1-fp8-h200-trt-mtp
+  description:
+    - "Update TensorRT-LLM image from v1.1.0rc2.post2 (154d/124d old) to v1.3.0rc14 (latest pre-release)"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1487