Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

$pwd:

hf-layer-package-jobs

Name: Hf Layer Package Jobs
Author: Mesh-LLM

// Use when changing mesh-llm automation or CLI flows that discover Hugging Face GGUF models, plan CPU Hugging Face Jobs for layer-package splitting, estimate max cost, or publish skippy layer packages/catalog entries.

In Manus ausführen

$ git log --oneline --stat

stars:1.083

forks:134

updated:8. Mai 2026 um 06:13

SKILL.md

readonly

name	hf-layer-package-jobs
description	Use when changing mesh-llm automation or CLI flows that discover Hugging Face GGUF models, plan CPU Hugging Face Jobs for layer-package splitting, estimate max cost, or publish skippy layer packages/catalog entries.
metadata	{"short-description":"Maintain HF layer package job automation"}

HF Layer Package Jobs

Use this skill for the models package CLI, the model-package crate, and the daily Unsloth queue workflow.

Workflow

Keep model refs in colon-selector form such as unsloth/Qwen3-8B-GGUF:Q4_K_M; do not split the quant into a separate --quant argument for generated job inputs.
Treat package submission as spend-bearing. The default behavior must be a dry run that prints the resolved package plan, effective timeout, selected HF Jobs hardware, and maximum cost. Require --confirm before submitting jobs.
Splitting is CPU and I/O bound. The HF Jobs hardware does not need enough RAM or VRAM to hold the full model; use CPU hardware suitable for running the splitter/build and scale timeout/cost estimates with model file size.
If the bucket script is stale during a confirmed submission, update it automatically before queuing jobs. Dry runs should avoid side effects.
The GitHub workflow should default to dry run. When confirmed, it should pass --confirm, submit at most the requested number of jobs, wait for every submitted HF Job, and fail if any job finishes unsuccessfully.
Prefer family-diverse candidate ordering after ranking by selected quant size, so one run does not consume the whole queue on a single model family.

Validation

Run Rust formatting and the focused package checks before committing:

cargo fmt --all -- --check
cargo test -p model-package
cargo check -p mesh-llm-host-runtime

For behavior smoke tests, use a tiny dry run first:

cargo run -p model-package --bin queue-unsloth-layer-packages -- --max-jobs 1 --recent-limit 3 --popular-limit 3 --dry-run

related-skills.json

gleiches Repository

skippy-bench.md

from "Mesh-LLM/mesh-llm"

Use this skill when running benchmark orchestration, local single-stage or split benchmarks, benchmark report flow, or performance-oriented skippy runtime checks.

2026-05-271.1k

skippy-correctness.md

from "Mesh-LLM/mesh-llm"

Use this skill when validating skippy staged execution against full-model execution, adding model families, changing split boundaries, testing activation wire dtypes, or diagnosing mismatch behavior.

2026-05-271.1k

skippy-model-package.md

from "Mesh-LLM/mesh-llm"

Use this skill when inspecting GGUF models, planning layer ranges, generating or validating skippy package artifacts, fake packages for direct GGUFs, materialized stage cache behavior, or GGUF writer integration.

2026-05-271.1k

skippy-server.md

from "Mesh-LLM/mesh-llm"

Use this skill when running, configuring, debugging, or embedding skippy-server, binary stage transport, OpenAI frontend integration, activation wire dtype settings, stage configs, lifecycle status, or nonblocking telemetry.

2026-05-271.1k

kv-tool-loop-stability.md

from "Mesh-LLM/mesh-llm"

Use this skill when certifying mesh-llm KV/cache stability under repeated OpenAI tool-call loops, same-prefix cache reuse, suffix-prefill limits, or native Skippy slot/decode/eviction failures.

2026-05-261.1k

telemetry-privacy-review.md

from "Mesh-LLM/mesh-llm"

Use this skill when adding, renaming, removing, or reviewing mesh-llm OTLP metrics, telemetry attributes, metrics exporter settings, or telemetry documentation.

2026-05-071.1k

package.json

"author": "Mesh-LLM"

"repository": "Mesh-LLM/mesh-llm"

GitHub-Repository öffnen Creator-Repositorys ansehen

$ install --global

$ download --local

In Manus ausführen

$ useful --forSOC

SoftwareentwicklerInformatik- und Mathematikberufe15-1252L4

name	hf-layer-package-jobs
description	Use when changing mesh-llm automation or CLI flows that discover Hugging Face GGUF models, plan CPU Hugging Face Jobs for layer-package splitting, estimate max cost, or publish skippy layer packages/catalog entries.
metadata	{"short-description":"Maintain HF layer package job automation"}

HF Layer Package Jobs

Use this skill for the models package CLI, the model-package crate, and the daily Unsloth queue workflow.

Workflow

Keep model refs in colon-selector form such as unsloth/Qwen3-8B-GGUF:Q4_K_M; do not split the quant into a separate --quant argument for generated job inputs.
Treat package submission as spend-bearing. The default behavior must be a dry run that prints the resolved package plan, effective timeout, selected HF Jobs hardware, and maximum cost. Require --confirm before submitting jobs.
Splitting is CPU and I/O bound. The HF Jobs hardware does not need enough RAM or VRAM to hold the full model; use CPU hardware suitable for running the splitter/build and scale timeout/cost estimates with model file size.
If the bucket script is stale during a confirmed submission, update it automatically before queuing jobs. Dry runs should avoid side effects.
The GitHub workflow should default to dry run. When confirmed, it should pass --confirm, submit at most the requested number of jobs, wait for every submitted HF Job, and fail if any job finishes unsuccessfully.
Prefer family-diverse candidate ordering after ranking by selected quant size, so one run does not consume the whole queue on a single model family.

Validation

Run Rust formatting and the focused package checks before committing:

cargo fmt --all -- --check
cargo test -p model-package
cargo check -p mesh-llm-host-runtime

For behavior smoke tests, use a tiny dry run first:

cargo run -p model-package --bin queue-unsloth-layer-packages -- --max-jobs 1 --recent-limit 3 --popular-limit 3 --dry-run

hf-layer-package-jobs

HF Layer Package Jobs

Workflow

Validation

Mehr aus diesem Repository

Mehr aus diesem Repository

HF Layer Package Jobs

Workflow

Validation