chore(recipes): remove 20 unused srt-slurm YAMLs / 删除 20 个未使用的 srt-slurm 配方 - #3465
Conversation
Remove 20 unused recipe files without changing active or deprecated config references. Generated matrices are unchanged.\n\n删除 20 个未引用的 srt-slurm 配方文件，不修改活动或已弃用配置的引用，生成矩阵保持不变。
|
Thanks for the contribution!
中文感谢你的贡献！
|
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
There was a problem hiding this comment.
Looks good, straightforward deletion-only cleanup. Reviewed: confirmed all 20 deleted recipe basenames/paths have zero remaining references in nvidia-master.yaml, amd-master.yaml, their deprecated counterparts, and perf-changelog.yaml; checked the kimik3/minimaxm3 single-node MI355X deletions specifically since amd-master.yaml still references sibling atom/mi355x-fp4-mtp/agentic.yaml paths (a different, unaffected variant); no code, launcher, or dependency files touched.
Extended reasoning...
Change is a pure deletion of 20 unreferenced srt-slurm recipe YAMLs (2632 lines removed, 0 added), no code/config/changelog files touched. Verified by grepping the deleted files' basenames and directory paths against nvidia-master.yaml, amd-master.yaml, both deprecated master configs, and perf-changelog.yaml, finding zero remaining references. No security-sensitive surface is touched; the only ambiguity (single-node MI355X recipes) resolved cleanly since active configs point at a differently-named atom/ variant, not the deleted vllm/ files.
…cipes # Conflicts: # benchmarks/single_node/srt-slurm-recipes/kimik3/vllm/mi355x-fp4-mtp/agentic.yaml
|
Kept 9 of the YAMLs this PR deleted (restored from
The PR now removes only the 11 |
2 participants
Summary
Remove 20 unreferenced srt-slurm recipe YAMLs, totaling 2,632 deleted lines:
No master config, launcher, dependency pin, retained recipe, or historical changelog is changed. This is a deletion-only cleanup against
8ec35e0e97c9f0846a132a4eb891b51e87d5e8b9, not a benchmark migration or model retirement.Audit boundaries
perf-changelog.yaml. Checked active and deprecated master configs, launchers, workflows, scripts, tests, docs, and other recipes. Single-node selection uses explicitsrt-recipe; multi-node selection usesCONFIG_FILE.8dace5f9596907a5075bf056251563b2e9563e7d) and NVIDIA/srt-slurm-recipes (2018b1dda0a2792edcb81fe7bae5293d25fd4ab2). Found no exact parsed-content duplicates to remove. The pinned runtime does not ship a historicalrecipes/tree, and InferenceX stages its local recipes explicitly; an upstream recipe with similar settings is not a safe drop-in replacement.configs/deprecatedas proposed in [Klaud Cold] Remove pointers to the deleted single-node bash folders; delete configs/deprecated and amd_utils/deprecated #3463.Validation
git diff --check: passed.All 413 unique active master-config recipe paths resolve. Deletion adds zero missing paths to active or deprecated configs. The deprecated NVIDIA config already has 398 missing legacy paths; those are unchanged.
Ran the real
generate_config_matriximplementation for each of 199 active config keys before and after deletion in both default and all-eval modes. Outputs are byte-identical, including errors:qwen3.5-fp4-b300-sglang-agentic-power-abandqwen3.5-fp8-b300-sglang-agentic-power-abreferencecluster:b300-nv, whoseavailable-cpu-dram-mibmetadata is absent. An unfiltered full-sweep fails for this same reason before any edits.Local matrix and SRT unit tests: 447 passed, 1 failed:
The failure is
test_pool_launcher_stages_artifacts_and_propagates_failure[h100-dgxc-slurm-none]: its environment lacksRUNNER_NAME. Reproduced the same failure in a clean worktree of the base commit. No test/source changes are included to conceal it.No GPU sweep or runtime-performance claim. No performance changelog entry: only unreferenced files are removed; no executed recipe or generated matrix changes.
AI model disclosure
GPT 6 Astra, via Perplexity Computer: repository audit, deletion selection, implementation, validation, and PR preparation. No delegated agents or additional models.
中文
概述
删除 20 个未被引用的 srt-slurm 配方 YAML，共减少 2,632 行：
本 PR 基于
8ec35e0e97c9f0846a132a4eb891b51e87d5e8b9，仅删除未引用文件，不修改主配置、启动器、依赖版本、保留配方或历史性能变更日志，不迁移基准测试，也不退役模型。审计范围
检查了单节点和多节点目录中的全部 765 个 YAML，包括 4 个共享 EPLB 文件。除历史
perf-changelog.yaml外，其他受版本控制的文本文件均未引用这些待删除配方的相对路径；检查覆盖活动及已弃用配置、启动器、工作流、脚本、测试、文档和其他配方。单节点通过显式srt-recipe选择配方，多节点使用CONFIG_FILE。保留活动配置引用的 413 个配方、仅已弃用配置引用的 328 个配方，以及被其他配方挂载使用的 4 个负载均衡 YAML。与 NVIDIA/srt-slurm 固定版本
8dace5f9596907a5075bf056251563b2e9563e7d和 NVIDIA/srt-slurm-recipes 的2018b1dda0a2792edcb81fe7bae5293d25fd4ab2比较后，未发现解析内容完全相同的配方。当前固定运行时不包含历史recipes/目录，不能因为上游存在相似配方就删除仍被引用的本地文件。本 PR 不涉及 #3390 的选择器工具或 #3391 的配方合并，也不执行 #3463 提出的
configs/deprecated删除。验证
git diff --check通过；活动配置引用的 413 个唯一配方路径全部存在。活动及已弃用配置均未新增缺失引用；已弃用 NVIDIA 配置原有的 398 个缺失历史路径保持不变。generate_config_matrix对 199 个活动配置逐一生成默认及全部评估模式的矩阵，输出及错误逐字节一致。197 个配置成功，分别生成 1,713 行和 1,652 行。qwen3.5-fp4-b300-sglang-agentic-power-ab和qwen3.5-fp8-b300-sglang-agentic-power-ab在修改前就因cluster:b300-nv缺少available-cpu-dram-mib而失败；完整 sweep 生成也受此影响。test_pool_launcher_stages_artifacts_and_propagates_failure[h100-dgxc-slurm-none]，其测试环境缺少RUNNER_NAME；已在基础提交的干净 worktree 复现。未修改测试或源码来掩盖问题。AI 模型披露
GPT 6 Astra，通过 Perplexity Computer 完成仓库审计、删除范围选择、实现、验证和 PR 准备。未委派其他代理，也未使用其他模型。