[AMD][MI355X] kimik3-fp4-mi355x-vllm-agentic-mtp a4w4 MoE + lmcache 0.5.6

[seungrokj]

Summary

• Switch kimik3-fp4-mi355x-vllm-agentic-mtp to the canonical VLLM_ROCM_USE_AITER_MOE_SITUV2=1 flag so the SiTUv2 a4w4 FlyDSL MoE path is selected unambiguously, and drop the deprecated AITER_SITUV2_A8W4 override.
• Bump the vLLM ROCm image to nightly-rocm100-29468dde and LMCache to 0.5.6.dev101+rocm7.2.
• Trim the search space to a single lmcache DRAM dcp-size 8 arm at conc [70, 80], dram-utilization 0.50.

Test plan

• e2e run: test-config --config-files ./configs/amd-master.yaml --config-keys kimik3-fp4-mi355x-vllm-agentic-mtp --no-evals

🤖 Generated with Claude Code

[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。

[seungrokj]

Need LMC fix on rocm env.

[functionstackx]

InferenceX has switched away from unmaintainable bash scripts to YAML files that don't repeat the same stuff over and over again. Please merge the latest main into this PR: we have migrated single-node AgentX onto native srt-slurm (#3428), so AgentX configs are now declarative YAML recipes, not per-config 1000+ line bash slop scripts. Please also delete the old benchmarks/single_node/** scripts (see this recipe for the new format).