Quark Torch LLM Ptq Eval
amd/Quark
L3 recipe that runs a Torch LLM PTQ end-to-end for AMD Quark — for PyTorch / HuggingFace transformers models (safetensors input): quantize → validate → evaluate.
Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation.
Install Atc Model Converter
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill atc-model-converter -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills atc-model-converter --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/inference/atc-model-converter .claude/skills/atc-model-converter && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "atc-model-converter" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/inference/atc-model-converter into .claude/skills/atc-model-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atc-model-converter", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/inference/atc-model-converterType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill atc-model-converter -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills atc-model-converter --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/inference/atc-model-converter .agents/skills/atc-model-converter && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "atc-model-converter" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/inference/atc-model-converter into .agents/skills/atc-model-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atc-model-converter", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill atc-model-converter -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills atc-model-converter --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/inference/atc-model-converter .cursor/skills/atc-model-converter && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "atc-model-converter" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/inference/atc-model-converter into .cursor/skills/atc-model-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atc-model-converter", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ascend-ai-coding/awesome-ascend-skills.git --path skills/inference/atc-model-converter--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill atc-model-converter -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills atc-model-converter --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/inference/atc-model-converter .gemini/skills/atc-model-converter && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "atc-model-converter" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/inference/atc-model-converter into .gemini/skills/atc-model-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atc-model-converter", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ascend-ai-coding/awesome-ascend-skills atc-model-converterInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill atc-model-converter -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/inference/atc-model-converter .github/skills/atc-model-converter && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "atc-model-converter" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/inference/atc-model-converter into .github/skills/atc-model-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atc-model-converter", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill atc-model-converter -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills atc-model-converter --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/inference/atc-model-converter .opencode/skills/atc-model-converter && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "atc-model-converter" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/inference/atc-model-converter into .opencode/skills/atc-model-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atc-model-converter", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
atc-model-converter- GitHub stars
- 174
- Token cost
- ~4.6k tokens
- SKILL.md length
- 649 words
- Files
- 13 (incl. scripts, references)
- Skills in repo
- 70
- Repo updated
- First seen
- Licence
- None found
At a glance
Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation.
- Works in 7 steps: 静态代码审查 (Static Analysis) → 动态探针注入 (Dynamic Probing) → 后处理类型识别 (Post-processing Identification) → …
- Deploying models on Ascend AI processors
- SKILL.md covers 开始之前：用户必须提供的信息, Workflow 1: 代码分析与参数发现 (Source…, Workflow 2: PyTorch → ONNX 导出 and Workflow 3: ONNX 检查 & ATC 转换, plus 5 more sections
- Runs Python and Shell scripts from its folder; calls python3 and pip; reaches github.com
What it does
Atc Model Converter is an agent skill from ascend-ai-coding/awesome-ascend-skills. Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation. Workflow 1 auto-discovers input shapes and parameters from user source code. Workflow 2 exports PyTorch models to ONNX. Workflow 3 converts ONNX to .om via ATC with multi-CANN version support. Workflow 4 adapts the user's full inference pipeline (preprocessing + model + postprocessing) to run end-to-end on NPU. Workflow 5 verifies precision between ONNX and OM outputs. Workflow 6 generates a reproducible README. Supports…
Its SKILL.md is about 4.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts and reference files (for example `references/AIPP_CONFIG.md`, `references/CANN_VERSIONS.md` and `references/EXAMPLE_README.md`).
It sits in AI & LLM Engineering, covering Deep learning and End-to-end testing. It works with ONNX and PyTorch. The repository describes itself as: A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed Agent Skills. https://ascend-ai-coding.github.io/awesome-ascend-skills/.
When your agent uses it
- Deploying models on Ascend AI processors
- Tasks that involve Deep learning
- Tasks that involve End-to-end testing
Example prompts
- “/atc-model-converter”
Requirements
- Python 3
- A Bash shell
Workflow steps
7 steps, taken from the step headings in SKILL.md.
- 静态代码审查 (Static Analysis)
- 动态探针注入 (Dynamic Probing)
- 后处理类型识别 (Post-processing Identification)
- 分析原始推理流程
- 构建端到端推理脚本
- 验证端到端结果
- 性能基准
What it can do on your machine
Read from SKILL.md and the folder at commit 62a4ecb. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 6 files in scripts/ (Python and Shell), which the agent can run.
Shell commands in SKILL.md call:
python3pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Atc Model Converter loads about 4.6k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 161 tokens; SKILL.md has 649 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 649 words (~4,594 tokens).
“华为昇腾 NPU 上完整的 PT -> ONNX -> OM 模型转换与端到端推理适配工具链。支持任意标准 PyTorch 或 ONNX 模型。”
- name
- atc-model-converter
- keywords
- ATC, inference, 模型转换, 推理, onnx, om, PyTorch, export, 导出, 精度对比
Files
SKILL.md and 12 other files (scripts, references) in skills/inference/atc-model-converter of ascend-ai-coding/awesome-ascend-skills.
- SKILL.md
- references/AIPP_CONFIG.md
- references/CANN_VERSIONS.md
- references/EXAMPLE_README.md
- references/FAQ.md
- references/INFERENCE.md
- references/PARAMETERS.md
- scripts/check_env_enhanced.sh
- scripts/compare_precision.py
- scripts/export_onnx.py
- scripts/get_onnx_info.py
- scripts/infer_om.py
- scripts/setup_env.sh
Open the folder on GitHubat commit 62a4ecb
Compare with similar skills
Atc Model Converter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Atc Model Converter this skillascend-ai-coding/awesome-ascend-skills | 174 | — | ~4.6k | Automated safety check: Pass | None | |
| Quark Torch LLM Ptq Evalamd/Quark | 181 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Embedded AI Deploymentmatlab/agent-skills-playground | 181 | 1 repos | ~3.4k | Automated safety check: Pass | Custom licence | |
| Model Builderqualcomm/qai-appbuilder | 246 | — | ~4.1k | Automated safety check: Pass | BSD-3-Clause | |
| PerforatedaiPerforatedAI/PerforatedAI | 237 | — | ~17k | Automated safety check: Pass | Apache-2.0 | |
| Matlab Import External AI Modelmatlab/matlab-agentic-toolkit | 1.1k | — | ~2.8k | Automated safety check: Pass | Custom licence |
Similar skills
Embedded AI Deployment
matlab/agent-skills-playground
Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder).
Model Builder
qualcomm/qai-appbuilder
QAI ModelBuilder. An agent skill from qualcomm/qai-appbuilder.
Perforatedai
PerforatedAI/PerforatedAI
Expert in PerforatedAI library for adding artificial dendrites to PyTorch neural networks.
Matlab Import External AI Model
matlab/matlab-agentic-toolkit
Import PyTorch, ONNX, or Keras 3 / TensorFlow 2.16+ deep learning models into MATLAB as dlnetwork objects.
Quark Create Shapeshifter Pass
amd/Quark
Author a new ShapeShifter graph-transformation pass for AMD Quark (ONNX or PyTorch) so it conforms to the pass framework's conventions and auto-registers.
More from ascend-ai-coding/awesome-ascend-skills
All 70 skills in this repoAscend Dmi
ascend-ai-coding/awesome-ascend-skills
当用户需要对华为昇腾 NPU 进行硬件层面的管理、测试或诊断时使用此 skill。典型场景： - 查看 NPU 卡的状态、温度、利用率 - 测试内存带宽（h2d/d2h/d2d/p2p） - 跑算力/功耗基准测试（TFLOPS、TOPS） - 诊断 NPU 硬件故障或做健康检查 - 对 NPU 卡做压力测试（aicore、内存） - 复位/恢复卡住或异常的 NPU 卡 典型用户问题（即使不提…
Ascendc
ascend-ai-coding/awesome-ascend-skills
End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project.
External Cannbot Ops Pypto Op Develop
ascend-ai-coding/awesome-ascend-skills
当需要编写 PyPTO 算子实现时使用此 skill。基于需求规格、设计方案和参考实现，生成完整可运行的 PyPTO 算子实现与配套测试、文档。Triggers: 实现算子、写 kernel、编写实现、写 impl、算子编码、开始编码、code the op、写 test、生成测试、写实现代码、op develop、kernel 实现。
External Gitcode Ascend Megatron Change Analyzer
ascend-ai-coding/awesome-ascend-skills
Analyze official Megatron-LM commits, PRs, and branch change sets to identify feature evolution, candidate breaking changes, and migration-relevant events.
External Gitcode Ascend Megatron Commit Tracker
ascend-ai-coding/awesome-ascend-skills
Track and normalize change requests against the official Megatron-LM repository by branch, PR, commit, commit range, or time window.
External Gitcode Ascend Megatron Impact Mapper
ascend-ai-coding/awesome-ascend-skills
Map migration-relevant Megatron changes onto the official MindSpeed repository by resolving branch alignment, locating affected subsystems, and identifying concrete adaptation points.
Related
Categories
Questions about Atc Model Converter
What does Atc Model Converter do?
Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation. Atc Model Converter is an agent skill from ascend-ai-coding/awesome-ascend-skills. Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation.
When should I use Atc Model Converter?
Atc Model Converter fits situations like: deploying models on Ascend AI processors; tasks that involve Deep learning; tasks that involve End-to-end testing.
How do I install Atc Model Converter in Claude Code?
Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill atc-model-converter -a claude-code`. Or copy the skill folder (skills/inference/atc-model-converter in ascend-ai-coding/awesome-ascend-skills) into .claude/skills/atc-model-converter in your project. Claude Code loads it when a task matches its description.
How do I install Atc Model Converter in Codex?
Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill atc-model-converter -a codex`. Or copy the skill folder (skills/inference/atc-model-converter in ascend-ai-coding/awesome-ascend-skills) into .agents/skills/atc-model-converter in your project. Codex loads it when a task matches its description.
Can I use Atc Model Converter in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill atc-model-converter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/atc-model-converter, .gemini/skills/atc-model-converter, .github/skills/atc-model-converter and .opencode/skills/atc-model-converter in your project.
What does Atc Model Converter need to run?
Going by SKILL.md and its folder, Atc Model Converter needs Python and a shell for the scripts in its folder and the command-line tools its instructions call (python3 and pip). Our summary lists: Python 3; A Bash shell.
Does Atc Model Converter access the network?
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Atc Model Converter safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Atc Model Converter use?
No licence was found for Atc Model Converter or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Atc Model Converter use?
About 4.6k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.
What are the alternatives to Atc Model Converter?
Skills that share tags, products or a category with Atc Model Converter: Quark Torch LLM Ptq Eval (amd/Quark, 181 stars), Embedded AI Deployment (matlab/agent-skills-playground, 181 stars), Model Builder (qualcomm/qai-appbuilder, 246 stars) and Perforatedai (PerforatedAI/PerforatedAI, 237 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Atc Model Converter?
ascend-ai-coding (a GitHub organization) maintains it in ascend-ai-coding/awesome-ascend-skills, which has 174 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 8, 2026.
Source: ascend-ai-coding/awesome-ascend-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.