claude

model-infer-optimize

NPU 模型推理端到端优化 Team。含 workflow、分析/实施/验证 Subagent,覆盖并行、KVCache/FA、融合算子、图模式、多流、预取和 SuperKernel。

0 on GitHubby CANNBotv1.0.3CANN-2.0updated 4 months agodevelopment
/

Plugin model-infer-optimize from marketplace cannbot in jieran-zhang/cannbot-skills. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Subagents (3)

  • model-infer-analyzer

    NPU 推理模型优化分析专家,负责模型架构分析、并行策略推荐、优化方案设计和性能 Profiling 数据解读。适用于模型结构理解、部署策略决策、各优化阶段的方案评估等分析类任务。

  • model-infer-implementer

    模型优化实施专家,负责按已确认方案实施代码改造和调试修复。适用于并行切分、算子替换、模式适配等各优化阶段的代码实施和问题修复。

  • model-infer-reviewer

    模型优化审查专家,负责验证代码改造的正确性、精度、性能和代码规范性,输出结构化诊断报告。适用于各优化阶段的精度验证、性能对比、策略校验、代码规范检查和仓库一致性审查。

Hooks (5)

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" session-start-model-infer

  • PreToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/pre_tool_use.py"

  • PreToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/time_reminder.py"

  • PostToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/post_tool_use.py"

  • SubagentStop

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/subagent_stop.py"

View source on GitHub gitcode.com

More from jieran-zhang/cannbot-skills

All 20 plugins →

AISS-TilingSolver:Ascend C 算子 Tiling 参数自动求解工具(MatMul / Vector)。下载安装、构造 JSON 输入、运行求解、结果解读与故障排查。

67 skills

0

Ascend C 代码审查 Skills(2 个)。代码审查规范和 API 文档检索。

67 skills

0

Ascend C Kernel 直调算子开发 Skills(40+ 个)。API 检索、Tiling 设计、精度调试、性能采集、环境检查、代码模板等。

67 skills

0

PyPTO 算子开发 Skills(8 个)。API 探索、Golden 生成、需求理解、算子设计与开发、性能调优、精度调试。

67 skills

0

TileLang 算子开发 Skills(9 个)。环境检查、子模块拉取、算子设计、算子开发、测试设计、API 最佳实践、编程模式指南、性能优化、代码审查。

67 skills

0

Triton-Ascend 算子代码生成与优化 Skills(6 个)。任务提取、算法设计、代码生成、功能验证、性能优化,以及 NPU 架构参考。

67 skills

0

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain model-infer-optimize?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins20 plugins