infx-bench-script-generator SKILL.md skillA
infx-bench-script-generator from shen-shanshan/vllm-dev-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add shen-shanshan/vllm-dev-skills/infx-bench-script-generator@git:20260929.ef4905bPins git:20260929.ef4905b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- shen-shanshan/vllm-dev-skills
- Path
skills/infx-bench-script-generator/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260929.ef4905b, committed Sep 29, 2026
- Size
- 5,328 bytes
- Repository stars
- 30
- License
- Apache-2.0
Generate three local bash scripts (docker run / server start / AgentX client replay) to run an InferenceX srt-slurm recipe YAML benchmark manually on a local GPU server, without Slurm or srt-slurm. Given a recipe like dsv4/vllm/mi355x-fp4-mtp/agentic.yaml and an override variant (e.g. override_tp8_c56 or override_dep8_c64), optionally capture one complete torch profiler prefill or decode step via vllm serve --profiler-config, with configurable host paths for model weights, the InferenceX…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# InferenceX 本地 Benchmark 脚本生成器
根据一个 InferenceX srt-slurm 单机 recipe（`xxx.yaml`）+ 一个 override variant，生成三份在
本地 GPU 服务器上手动跑 AgentX benchmark 的脚本（不依赖 Slurm / srt-slurm / GitHub Actions）。
## 输入（缺失项向用户确认，路径可留空走默认）
1. recipe 路径（如 `dsv4/vllm/mi355x-fp4-mtp/agentic.yaml`，相对于 InferenceX 仓库的
`inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/`，或绝对路径）
2. override 名（如 `override_tp8_c56`、`override_dep8_c64`；也接受 `base`）
3. 是否采集 torch profiler trace：`off`（默认）/ `prefill`（一个完整 prefill step）/
`decode`（一个完整 decode step）
4. 模型权重 host 路径（留空 = server 脚本在容器内下载，存 named volume）
5. InferenceX 仓库 host 路径（留空 = client 脚本在容器内 clone）
6. trace 数据集 host 路径（留空 = 挂载 host `~/.cache/huggingface`，复用缓存与 HF token）
7. 测试结果 host 目录（留空 = named volume 挂到 `/logs`，即 InferenceX 默认结果位置）
## 工作流程
1. **读 recipe 并自检**：读目标 yaml，确认 override 存在；需要 schema/merge 规则细节时读
[`references/recipe-schema.md`](references/recipe-schema.md)（含 dsv4 mi355x 的 worked example）。
2. **运行生成器**（产物由脚本确定性生成，不要手写这三个文件）：
```bash
python3 <skill_dir>/scripts/gen_bench_scripts.py \
--recipe <recipe 绝对路径> --override <override 名> \
[--model-path <host 路径>] [--repo-path <host 路径>] \
…Read the whole file at its exact version.
How to install
mdr add shen-shanshan/vllm-dev-skills/infx-bench-script-generator@sha256:0f7b7fa8cfce2104The line at the top of this page pins the label git:20260929.ef4905b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_qqokcsnroymhzdvd)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 29, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5328 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
shen-shanshan/vllm-dev-skills · 30 stars · license Apache-2.0 · pushed 2026-11-05 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_qqokcsnroymhzdvd GET https://markdownregistry.com/api/v1/resolve?ref=shen-shanshan/vllm-dev-skills/infx-bench-script-generator GET https://markdownregistry.com/api/v1/blob/0f7b7fa8cfce21040ad86e25c3ae4ff15825c1e0f553e47c312c0c4509673fdc
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.