Hugging Face Local Model Evals
huggingface/skills
Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.
Adds Liger Kernel support for a new HuggingFace Transformers model, or modifies existing monkey-patching.
Install Liger Autopatch
$ npx skills add linkedin/Liger-Kernel --skill liger-autopatch -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install linkedin/Liger-Kernel liger-autopatch --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/linkedin/Liger-Kernel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/liger-autopatch .claude/skills/liger-autopatch && 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 "liger-autopatch" agent skill from https://github.com/linkedin/Liger-Kernel/tree/main/.agents/skills/liger-autopatch into .claude/skills/liger-autopatch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "liger-autopatch", 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/linkedin/Liger-Kernel/tree/main/.agents/skills/liger-autopatchType 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 linkedin/Liger-Kernel --skill liger-autopatch -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install linkedin/Liger-Kernel liger-autopatch --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linkedin/Liger-Kernel.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/liger-autopatch .agents/skills/liger-autopatch && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "liger-autopatch" agent skill from https://github.com/linkedin/Liger-Kernel/tree/main/.agents/skills/liger-autopatch into .agents/skills/liger-autopatch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "liger-autopatch", 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 linkedin/Liger-Kernel --skill liger-autopatch -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install linkedin/Liger-Kernel liger-autopatch --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linkedin/Liger-Kernel.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/liger-autopatch .cursor/skills/liger-autopatch && 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 "liger-autopatch" agent skill from https://github.com/linkedin/Liger-Kernel/tree/main/.agents/skills/liger-autopatch into .cursor/skills/liger-autopatch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "liger-autopatch", 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/linkedin/Liger-Kernel.git --path .agents/skills/liger-autopatch--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 linkedin/Liger-Kernel --skill liger-autopatch -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install linkedin/Liger-Kernel liger-autopatch --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linkedin/Liger-Kernel.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/liger-autopatch .gemini/skills/liger-autopatch && 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 "liger-autopatch" agent skill from https://github.com/linkedin/Liger-Kernel/tree/main/.agents/skills/liger-autopatch into .gemini/skills/liger-autopatch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "liger-autopatch", 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 linkedin/Liger-Kernel liger-autopatchInstalls 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 linkedin/Liger-Kernel --skill liger-autopatch -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/linkedin/Liger-Kernel.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/liger-autopatch .github/skills/liger-autopatch && 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 "liger-autopatch" agent skill from https://github.com/linkedin/Liger-Kernel/tree/main/.agents/skills/liger-autopatch into .github/skills/liger-autopatch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "liger-autopatch", 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 linkedin/Liger-Kernel --skill liger-autopatch -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install linkedin/Liger-Kernel liger-autopatch --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linkedin/Liger-Kernel.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/liger-autopatch .opencode/skills/liger-autopatch && 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 "liger-autopatch" agent skill from https://github.com/linkedin/Liger-Kernel/tree/main/.agents/skills/liger-autopatch into .opencode/skills/liger-autopatch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "liger-autopatch", 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
liger-autopatch- GitHub stars
- 6.7k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 469 words
- Files
- 12
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- BSD-2-Clause
At a glance
Adds Liger Kernel support for a new HuggingFace Transformers model, or modifies existing monkey-patching.
- Works in 6 steps: Analyze → Generate → Validate → …
- Adding a new model to Liger Kernel
- SKILL.md covers Mode Detection, Pipeline (Create Mode), Pipeline (Modify Mode) and Reference Files
- Calls pytest and make
What it does
Liger Autopatch is an agent skill from linkedin/Liger-Kernel. Adds Liger Kernel support for a new HuggingFace Transformers model, or modifies existing monkey-patching. Generates lceforward, monkey-patch function, tests, and README entry. Use when adding a new model to Liger Kernel, when a user asks to patch an unsupported model, when extending MODELTYPETOAPPLYLIGERFN, or when modifying/updating/fixing an existing monkey-patch (e.g., adding a new kernel to an already-supported model, fixing instance patching, updating a patch for upstream HF changes).
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files (for example `code-generator.md`, `decision-matrix.md` and `examples/gemma-profile.md`).
It sits in AI & LLM Engineering, covering GPU and accelerator computing. It works with Transformers and Mistral AI. The repository describes itself as: Efficient Triton Kernels for LLM Training. The licence is BSD-2-Clause.
When your agent uses it
- Adding a new model to Liger Kernel
- A user asks to patch an unsupported model
- Extending MODELTYPETOAPPLYLIGERFN
- Modifying/updating/fixing an existing monkey-patch (e.g.
Example prompts
- “/liger-autopatch”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit d5f2817. 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
Shell commands in SKILL.md call:
pytestmake
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Liger Autopatch loads about 1.3k tokens when it runs. Until then it costs about 129 tokens; SKILL.md has 469 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from linkedin/Liger-Kernel at commit d5f2817, republished under its BSD-2-Clause licence (© linkedin). 469 words, ~1,283 tokens.
Download SKILL.mdSave it as
.claude/skills/liger-autopatch/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.- name
- liger-autopatch
- description
- Adds Liger Kernel support for a new HuggingFace Transformers model, or modifies existing monkey-patching. Generates lce_forward, monkey-patch function, tests, and README entry. Use when adding a new model to Liger Kernel, when a user asks to patch an unsupported model, when extending MODEL_TYPE_TO_APPLY_LIGER_FN, or when modifying/updating/fixing an existing monkey-patch (e.g., adding a new kernel to an already-supported model, fixing instance patching, updating a patch for upstream HF changes).
Liger Auto-Patch
Adds Liger Kernel optimization support for a new HuggingFace model, or modifies existing monkey-patching, through a staged pipeline with human review between stages. Supports creating new model patches and modifying existing ones.
Mode Detection
- Create mode: User asks to add/patch/support a new model → full pipeline (Analyze → Generate → Validate)
- Modify mode: User asks to update/fix/change/extend an existing monkey-patch → lighter pipeline (Change Impact Analysis → Apply Changes → Validate)
Keywords that suggest modify mode: update, fix, change, add [kernel] to [existing model], extend, modify, new activation, new norm, bug in patch, upstream changed
Pipeline (Create Mode)
Stage 1: Analyze
Follow the Model Analyzer workflow in model-analyzer.md. If the host runtime supports parallel subagents, this stage may be delegated to one; otherwise execute the workflow directly.
This stage reads the HF modeling_*.py source and produces a model profile answering 12 architectural questions from decision-matrix.md.
Human checkpoint: Present the profile. Confirm before proceeding.
Stage 2: Generate
Follow the Code Generator workflow in code-generator.md.
Generates/modifies up to 13 files:
src/liger_kernel/transformers/model/{model}.py— NEW lce_forwardsrc/liger_kernel/transformers/monkey_patch.py— MODIFYsrc/liger_kernel/transformers/__init__.py— MODIFYsrc/liger_kernel/transformers/model/output_classes.py— MODIFY if neededtest/transformers/test_monkey_patch.py— MODIFYtest/convergence/bf16/test_mini_models.py— MODIFY (FLCE path)test/convergence/bf16/test_mini_models_with_logits.py— MODIFY (non-FLCE path)test/convergence/fp32/test_mini_models.py— MODIFY (FLCE path)test/convergence/fp32/test_mini_models_with_logits.py— MODIFY (non-FLCE path)test/convergence/bf16/test_mini_models_multimodal.py— MODIFY if VL modeltest/convergence/fp32/test_mini_models_multimodal.py— MODIFY if VL modeltest/utils.py— MODIFYREADME.md— MODIFY
Human checkpoint: Present changes for review.
Stage 3: Validate
Follow the Validator workflow in validator.md.
Runs instance patching test, convergence test, and lint check. Retries up to 3 times on failure.
Human checkpoint: Report final test results.
Pipeline (Modify Mode)
Show full SKILL.md (209 more words)Show less
Stage 1: Change Impact Analysis
Read the existing apply_liger_kernel_to_{model_type} function in monkey_patch.py and the relevant section of the upstream HF modeling_{model_type}.py. Produce a short change plan:
- What is being added/changed/fixed
- Which Liger kernel(s) are involved
- Which files need modification (subset of the 13 files from create mode)
- What the expected behavior should be after the change
Human checkpoint: Present the change plan. Confirm before proceeding.
Stage 2: Apply Changes
Follow the Code Generator workflow in code-generator.md in modify mode.
Human checkpoint: Present changes for review.
Stage 3: Validate
Follow the Validator workflow in validator.md. This stage is mandatory — do not skip it. At minimum, run:
- Instance patching test:
pytest test/transformers/test_monkey_patch.py -k "{model_type}" -xvs - All convergence tests for the model:
pytest test/convergence/bf16/test_mini_models.py -k "{model_type}" -xvs(FLCE, bf16)pytest test/convergence/bf16/test_mini_models_with_logits.py -k "{model_type}" -xvs(non-FLCE, bf16)pytest test/convergence/fp32/test_mini_models.py -k "{model_type}" -xvs(FLCE, fp32)pytest test/convergence/fp32/test_mini_models_with_logits.py -k "{model_type}" -xvs(non-FLCE, fp32)- If VL (multimodal) model, also run:
pytest test/convergence/bf16/test_mini_models_multimodal.py -k "{model_type}" -xvspytest test/convergence/fp32/test_mini_models_multimodal.py -k "{model_type}" -xvs
- Checkstyle:
make checkstyle
Human checkpoint: Report final test results.
Reference Files
- decision-matrix.md — 12 architectural decisions to resolve per model
- examples/llama-profile.md — Reference profile for standard dense model
- examples/gemma-profile.md — Reference profile showing GeGLU + offset variant
- Templates in templates/ — Code generation patterns for each file type
© linkedin, BSD-2-Clause. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 11 other files in .agents/skills/liger-autopatch of linkedin/Liger-Kernel.
- SKILL.md
- code-generator.md
- decision-matrix.md
- examples/gemma-profile.md
- examples/llama-profile.md
- model-analyzer.md
- templates/lce-forward-dense.md
- templates/lce-forward-moe.md
- templates/monkey-patch-fn.md
- templates/test-convergence.md
- templates/test-instance-patch.md
- validator.md
Open the folder on GitHubat commit d5f2817
Compare with similar skills
Liger Autopatch 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 |
|---|---|---|---|---|---|---|
| Liger Autopatch this skilllinkedin/Liger-Kernel | 6.7k | — | ~1.3k | Automated safety check: Pass | BSD-2-Clause | |
| Hugging Face Local Model Evalshuggingface/skills | 11k | 2 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Hugging Face Vision Trainerhuggingface/skills | 11k | 1 repos | ~7.5k | Automated safety check: Pass | Apache-2.0 | |
| bitsandbytes Model QuantizationOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Quark Torch LLM Ptq Evalamd/Quark | 181 | — | ~2.6k | Automated safety check: Pass | MIT | |
| LLM Torch Profiler Trace AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS | 925 | — | ~2.8k | Automated safety check: Pass | None |
Similar skills
- Official
- Official
Hugging Face Vision Trainer
huggingface/skills
Trains and fine-tunes object detection, image classification and SAM or SAM2 segmentation models on Hugging Face Jobs cloud GPUs and saves the results to the Hub.
bitsandbytes Model Quantization
Orchestra-Research/AI-Research-SKILLs
Loads large language models in 8-bit or 4-bit with bitsandbytes so they fit smaller GPUs, and sets up QLoRA fine-tuning on a 4-bit base model.
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.
LLM Torch Profiler Trace Analysis
BBuf/AI-Infra-Auto-Driven-SKILLS
Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.
Cuda Cpp Kernel
vipshop/cache-dit
A skill your agent uses when writing, debugging, porting, reviewing, or optimizing CUDA C++ or PTX kernels; investigating CUDA Runtime or Driver API behavior; profiling kernels with Nsight Systems…
More from linkedin/Liger-Kernel
Liger Kernel Dev
linkedin/Liger-Kernel
Develops production-ready Triton kernels for Liger Kernel. An agent skill from linkedin/Liger-Kernel.
Liger Kernel Perf
linkedin/Liger-Kernel
Optimizes the performance of existing Liger Kernel Triton kernels.
Related
Works with
Categories
Questions about Liger Autopatch
What does Liger Autopatch do?
Adds Liger Kernel support for a new HuggingFace Transformers model, or modifies existing monkey-patching. Liger Autopatch is an agent skill from linkedin/Liger-Kernel. Adds Liger Kernel support for a new HuggingFace Transformers model, or modifies existing monkey-patching.
When should I use Liger Autopatch?
Liger Autopatch fits situations like: adding a new model to Liger Kernel; A user asks to patch an unsupported model; extending MODELTYPETOAPPLYLIGERFN; modifying/updating/fixing an existing monkey-patch (e.g.
How do I install Liger Autopatch in Claude Code?
Run `npx skills add linkedin/Liger-Kernel --skill liger-autopatch -a claude-code`. Or copy the skill folder (.agents/skills/liger-autopatch in linkedin/Liger-Kernel) into .claude/skills/liger-autopatch in your project. Claude Code loads it when a task matches its description.
How do I install Liger Autopatch in Codex?
Run `npx skills add linkedin/Liger-Kernel --skill liger-autopatch -a codex`. Or copy the skill folder (.agents/skills/liger-autopatch in linkedin/Liger-Kernel) into .agents/skills/liger-autopatch in your project. Codex loads it when a task matches its description.
Can I use Liger Autopatch 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 linkedin/Liger-Kernel --skill liger-autopatch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/liger-autopatch, .gemini/skills/liger-autopatch, .github/skills/liger-autopatch and .opencode/skills/liger-autopatch in your project.
What does Liger Autopatch need to run?
Going by SKILL.md and its folder, Liger Autopatch needs the command-line tools its instructions call (pytest and make).
Does Liger Autopatch access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Liger Autopatch 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. Review the folder before installing.
What licence does Liger Autopatch use?
Liger Autopatch is published under the BSD-2-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Liger Autopatch use?
About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Liger Autopatch?
Skills that share tags, products or a category with Liger Autopatch: Hugging Face Local Model Evals (huggingface/skills, 11k stars), Hugging Face Vision Trainer (huggingface/skills, 11k stars), bitsandbytes Model Quantization (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Quark Torch LLM Ptq Eval (amd/Quark, 181 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Liger Autopatch?
linkedin (a GitHub organization) maintains it in linkedin/Liger-Kernel, which has 6,652 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 8, 2026.
Source: linkedin/Liger-Kernel on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.