AGENT SKILL

module-computation

Compute evaluate metrics, comparisons, and measurements with direct or streaming inputs; combine modules; configure cache/distributed runs; save results; and debug input validation.

License 许可
Apache-2.0
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
module-computation
license
Apache 2.0
metadata
{ "disco-role": "operating" }
description
Compute evaluate metrics, comparisons, and measurements with direct or streaming inputs; combine modules; configure cache/distributed runs; save results; and debug input validation.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

Module Computation

Use this sub-skill when a user has already selected or loaded an evaluate module and needs to run it correctly. Route module discovery, Hub/local loading, revisions, and evaluate.load(...) decisions to ../module-loading/. Route evaluator pipeline orchestration around datasets/models/pipelines to ../evaluator-pipelines/. Route authoring or sharing new modules to ../hub-and-cli/.

Start Here

  1. Inspect the loaded module before computing: check module.features, module.inputs_description, module.module_type, and module.info so input names and shapes match the module contract.
  2. Choose a computation style:
    • Direct: module.compute(predictions=[...], references=[...], **module_kwargs) for all inputs at once.
    • Streaming examples: call module.add(prediction=..., reference=...) repeatedly, then module.compute().
    • Streaming batches: call module.add_batch(predictions=[...], references=[...]) for each batch, then module.compute().
  3. For non-standard modules, use the input names shown in features, such as inputs= and targets=, instead of assuming predictions/references.
  4. For multiple modules, use evaluate.combine(...); pass force_prefix=True or a name-to-module dict when output keys may collide.
  5. For distributed runs, set the same cache_dir, num_process, and experiment_id on every worker, a unique process_id per worker, and read the result only from process_id == 0.
  6. Save finished result dictionaries with evaluate.save(path_or_file, **result, **metadata) when the user needs a JSON record.

Core References

  • references/computation-workflows.md: direct compute, streaming, combined evaluations, distributed/cache patterns, result saving, and integration examples.
  • references/api-reference.md: signatures, accepted inputs, result shapes, and constructor/settings table for computation APIs.
  • references/troubleshooting.md: validation, shape, cache, distributed, casting, and combined-key failure modes.
  • scripts/compute_smoke.py: safe smoke helper for tiny computations against a named module or local module path.

Fast Patterns

import evaluate

metric = evaluate.load("accuracy")
result = metric.compute(predictions=[0, 1, 1, 0], references=[0, 1, 0, 1])
metric = evaluate.load("accuracy")
for predictions, references in [([0, 1], [0, 1]), ([1, 0], [0, 1])]:
    metric.add_batch(predictions=predictions, references=references)
result = metric.compute()
combined = evaluate.combine({"acc": "accuracy", "f1_binary": "f1"}, force_prefix=True)
result = combined.compute(predictions=[0, 1, 0], references=[0, 1, 1])

Guardrails

  • compute, add, and add_batch are keyword-oriented for EvaluationModule; do not rely on positional calls for normal modules.
  • features describes one example; add_batch and compute usually receive lists, arrays, or tensors of those examples.
  • add takes singular aliases (prediction, reference) for standard modules; use custom feature names directly for non-standard modules.
  • compute() returns None on non-zero distributed processes; only process 0 returns the final result dict.
  • keep_in_memory=True is single-process only; do not combine it with num_process > 1.
  • evaluate.save records metadata including interpreter information in the JSON output; avoid publishing sensitive local paths from saved files without review.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351