Integrate the TileRT srt-slurm fork stack

[cquil11]

Shared integration for MI355X AgentX #3552 and B200 fixed-sequence #3553.

• Pin the per-role engine and TileRT fork stack.
• Select golden acceptance for TileRT decode without altering vLLM prefill.
• Support explicit benchmark model names and request counts, and scrape only the prefill metrics endpoint.

Workload recipes and removal of their legacy launch paths are in the child PRs.

Validation:

• B200 1k1k and 8k1k: passed, 16/16 requests each; 8k1k power validated across 16 GPUs on two nodes.
• MI355X AgentX: passed, full 3,600-second profile, 271 successful requests and zero errors; vLLM metrics validated.

[github-actions]

Thanks for the contribution!

• Review: If this PR changes files owned by someone other than a repository admin or @SemiAnalysisAI/core, ask one eligible CODEOWNER to complete the latest PR_REVIEW_CHECKLIST.md before contacting a core maintainer on Slack. Follow the template exactly, including As a PR reviewer and CODEOWNER, I have reviewed this and have, so sign-off verification triggers.
• PR verification: Sweeps only run on labeled PRs. Add full-sweep-fail-fast (strongly recommended); use full-sweep-enabled only when matrix jobs should continue after a failure.
• After merging: PR authors must ensure all GitHub Actions jobs pass. Transient failures often pass on rerun; see how to rerun failed jobs.

中文

感谢你的贡献！

• **审阅：**如果 PR 修改的文件归属于仓库管理员及 @SemiAnalysisAI/core 之外的 CODEOWNER，请先联系一位有资格的 CODEOWNER 填写最新的 PR_REVIEW_CHECKLIST.md，再通过 Slack 联系核心维护者。必须严格遵循模板，并保留 As a PR reviewer and CODEOWNER, I have reviewed this and have，才能触发签核验证。
• **PR 验证：**扫描仅在带有标签的 PR 上运行。强烈建议添加 full-sweep-fail-fast；仅当需要矩阵任务在失败后继续运行时才使用 full-sweep-enabled。
• **合并后：**PR 作者必须确保所有 GitHub Actions 任务通过。临时性失败通常可以通过重新运行恢复；参见重新运行失败任务的说明。