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

[functionstackx]

Summary

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

• dsr1-fp8-b200-trt: nvcr.io#nvidia/tensorrt-llm/release:1.2.0rc6.post2 → nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14
• dsr1-fp8-b200-trt-mtp: nvcr.io#nvidia/tensorrt-llm/release:1.2.0rc6.post3 → nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14

Test plan

• full-sweep-enabled sweep passes.

🤖 Generated with Claude Code

[github-actions]

Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook

• https://docs.sglang.io/cookbook/intro
• https://recipes.vllm.ai/

If it is not, please create a PR first before we can merge your single node PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you

• https://github.com/vllm-project/recipes
• https://github.com/sgl-project/sglang/tree/main/docs_new

PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow

As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers.

If additional help is needed, PR authors can reach out to core maintainers over Slack.

[github-actions]

Thanks for the contribution! For vLLM & SGLang, please ensure that your recipes is similar to the official vLLM recipes and/or the SGLang cookbook

• https://docs.sglang.io/cookbook/intro
• https://recipes.vllm.ai/

If it is not, please create a PR first before we can merge your single node PR into the master branch. Let's ensure that the documentation is first class such that the entire ML community can benefit from your hard work! Thank you

• https://github.com/vllm-project/recipes
• https://github.com/sgl-project/sglang/tree/main/docs_new

PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. If re-running failed jobs is attempted, PR authors are responsible for ensuring it passes. See GitHub's docs on re-running failed jobs: https://docs.github.com/en/actions/how-tos/manage-workflow-runs/re-run-workflows-and-jobs#re-running-failed-jobs-in-a-workflow

As a rule of thumb, generally, PR authors should request a review & get a PR approval from the respective companies' CODEOWNERS before requesting a review from core maintainers.

If additional help is needed, PR authors can reach out to core maintainers over Slack.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26016871706
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26016871706

[claude]

LGTM, straightforward TRT-LLM image version bump with matching changelog entry.

Extended reasoning...

Overview

This PR bumps the TensorRT-LLM image for two configs (dsr1-fp8-b200-trt and dsr1-fp8-b200-trt-mtp) from v1.2.0rc6.post2/v1.2.0rc6.post3 to v1.3.0rc14 in .github/configs/nvidia-master.yaml, and adds a corresponding entry to perf-changelog.yaml.

Security risks

None. These are YAML config changes pointing to an official NVIDIA NGC image (nvcr.io#nvidia/tensorrt-llm/release), and there is no executable code being introduced.

Level of scrutiny

Low. This is a mechanical, auto-generated image version bump (Klaud Cold) of the kind that lands routinely in this repo — see recent commits like fc84ab7 (the previous TRT-LLM update for the same configs) and similar SGLang/vLLM image bumps. Correctness is enforced by the full-sweep-enabled label triggering a sweep job.

Other factors

The bug hunting system found no issues, the changelog entry correctly references PR #1488 with accurate before/after image tags, and the change pattern exactly mirrors prior approved image bumps in this repository.

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26016874169
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26016874169

[functionstackx]

/reuse-sweep-run

[github-actions]

see unofficial run visualizer at https://inferencex.semianalysis.com/inference?unofficialRun=26045823723
see unofficial run visualizer at https://inferencex.semianalysis.com/evaluation?unofficialRun=26045823723