Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add shen-shanshan/vllm-dev-skills --skill vllm-vs-atom-decode-trace-comparisongit clone --depth 1 https://github.com/shen-shanshan/vllm-dev-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-vs-atom-decode-trace-comparison)<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-vs-atom-decode-trace-comparison"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-vs-atom-decode-trace-comparison/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-vs-atom-decode-trace-comparison"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-vs-atom-decode-trace-comparison.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01582 |
| Opus 5.5 | $0.00000 | $0.00633 |
| Sonnet 5.5 | $0.00000 | $0.00316 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade A, and why
vllm-vs-atom-decode-trace-comparison scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vLLM vs ATOM Decode Trace 对比分析
目标与输入
产出一份 Markdown 对比报告:同一模型、同一配置下 vLLM 与 ATOM 的 decode 阶段 GPU kernel 实现差异, 并对每类层生成对比表 + vLLM 优化 TODO 清单。
需要 4 个输入(缺失则询问用户):
- 模型名(如
MiniMaxAI/MiniMax-M3) - vllm trace 路径(torch profiler 导出的 Chrome-trace JSON,可
.gz) - atom trace 路径(同上)
- 报告语言:
zh(默认)/en/both
第 1 步先向用户确认"两份 trace 是同模型同配置跑的"这一前提;若用户不确认, 在报告 §1 中显式标注风险。配置明显不同(GPU 数量、引擎版本差异过大)时提醒用户,不拒绝执行。
运行提取脚本
对两份 trace 各执行一次(产物写入本 skill 的 outputs/):
python3 <skill_dir>/scripts/extract_trace.py --trace <vllm_trace.json> --output-dir <skill_dir>/outputs
python3 <skill_dir>/scripts/extract_trace.py --trace <atom_trace.json> --output-dir <skill_dir>/outputs
stdout 会给出 digest: 与 slice: 两个产物路径,以及 engine/steps/chosen_step/kernels/distinct/replay_stable/busy_pct 摘要。
- 脚本自动:识别引擎(顶层 key)、用 gpu 通道
execute_context_*注解切分 decode step、跳过首尾窗口选中间 step、 对每个 kernel 名做统计(count/mean/median/sum/streams)、取中间 occurrence 作单层样本、输出 digest(.md) + slice(.json)。 - 一般无需调参。仅当 digest 异常(如
replay_stable: False且回退窗口可疑)时才用--step-index N/--occurrence N覆盖;trace 无 gpu 注解时用--bracket cpu-annot(结果标注为近似)。 - 退出码 2 = trace 没有 step 注解(需用带 profiler 注解的方式重新采集),此时停止并向用户说明。
加载领域知识
必须完整阅读 references/analysis_guide.md 后再开始解释数据。该文件包含:
trace 格式事实、步骤切分原理、layer 识别方法(occurrence-index)、逻辑算子分组规则、
多流检测、对比表与 TODO 编写规则、pitfalls、报告模板、以及 MiniMax-M3 的完整 worked example
(含两引擎真实 kernel 清单,可作方法论参照——其它模型按同样流程处理)。
逐层类型对比流程
- 校验可比性:读两份 digest 的 §1-§3。确认引擎识别正确、窗口可比、
busy/wall在 ~90-100%、 replay_stable 状态一致。不一致时在报告 §6 说明。 - 判定层型与选中层:按 guide §3,用计数族 + kernel 模板变体 + ts 位置判定该模型的层类型分布,
每类层选一个中间层(digest §5 的 middle-occurrence 行即该层样本)。
若模型有 HF config 可查(网络可用时用模型名查
num_hidden_layers、dense/sparse 层分布),与计数族互证。 - 归组逻辑算子:按 guide §4 的标准 forward 序列把每类层的 kernel 归组为逻辑算子;
对不认识的 kernel 名,用 digest §7 的全名在对应引擎仓库 grep(vllm:
csrc/、vllm/_custom_ops.py; ATOM/aiter:csrc/),确认语义后再归组。 - 生成对比表:每类层一张表(模板见 guide §6/§8)。数字只取自 digest/slice:
count×mean归一为单层单次 µs;差异 <5% 持平、5-20% 略、>20% 显著。 - 派生 TODO 清单:按 guide §6 规则,只对 atom 更快且差异可复现的算子写 TODO(写给 vLLM), 按预期收益排序。
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- outputs/atom-minimax-m3-tp4-8k1k-conc8_digest.md 30 KB
- outputs/atom-minimax-m3-tp4-8k1k-conc8_slice.json 54 KB
- outputs/minimax-m3-trace-comparison_zh_20260905_162716.md 16 KB
- outputs/vllm-minimax-m3-tp4-8k1k-conc8_digest.md 33 KB
- outputs/vllm-minimax-m3-tp4-8k1k-conc8_slice.json 60 KB
- references/analysis_guide.md 15 KB
- scripts/extract_trace.py 20 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 78 lines · 0 tokens per session scan A b39d80a73ea4
vllm-vs-atom-decode-trace-comparison is a skill published in the GitHub repository shen-shanshan/vllm-dev-skills (22 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,582 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
routing-calibration
Use when calibrating or validating a maintained routing recipe against live model backends, including probe manifests and evidence reports.
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
moai-workflow-ddd
Domain-Driven Development workflow specialist using ANALYZE-PRESERVE-IMPROVE cycle for behavior-preserving code transformation. Use when refactoring legacy code or reducing technical debt safely.
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
cherry-assistant-guide
A guide for looking up Cherry Studio's product details and diagnosing problems such as connection failures, setup errors, and runtime issues.
cherry-electron-dev
Develop, fix, profile, and test PRs in a tracked Cherry Studio Electron instance. Use for implementation, UI and interaction work, runtime debugging, DevTools inspection, performance analysis, and interactive PR verification with a test report. Reuse a verified workspace instance and manage its lifetime according to…