AGENT SKILL

training-and-configs

Assemble verl PPO, GRPO, SFT, and on-policy distillation training commands, Hydra overrides, backend strategy switches, and config troubleshooting guidance.

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

01 前言 Front Matter

name
training-and-configs
license
Apache 2.0
metadata
{ "disco-role": "operating" }
description
Assemble verl PPO, GRPO, SFT, and on-policy distillation training commands, Hydra overrides, backend strategy switches, and config troubleshooting guidance.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

training-and-configs

Use this sub-skill when a coding agent needs to build or debug verl training commands and Hydra config overrides for PPO-like RL, GRPO, SFT, or on-policy distillation.

Route by Task

  • PPO / critic training: Use references/training-workflows.md for the python -m verl.trainer.main_ppo command shape, required actor/critic/model/data/logger overrides, and FSDP or Megatron examples.
  • GRPO / critic-less RL: Use references/training-workflows.md for algorithm.adv_estimator=grpo, grouped rollout n, KL-loss settings, and no-critic command patterns.
  • SFT: Use references/training-workflows.md for torchrun -m verl.trainer.sft_trainer, engine=fsdp, dataset message keys, LoRA/PEFT, and sequence-parallel switches.
  • On-policy distillation: Use references/training-workflows.md for distillation.enabled=True, teacher resource sizing, teacher model overrides, and distillation loss modes.
  • Hydra and backend switches: Use references/configuration.md before changing model_engine, FSDP/FSDP2, Megatron, VeOmni, TorchTitan, rollout backend, batch, checkpoint, logger, or generated-reference config fields.
  • Failures and validation errors: Use references/troubleshooting.md for overlong prompts, OOM, Hydra override syntax, config-doc CI, rollout backend mismatch, Ray/GPU resource, and distillation teacher sizing problems.

Bundled Tool

  • scripts/build_ppo_command.py assembles a dry-run python -m verl.trainer.main_ppo command from common data, model, rollout, backend, batch, and logger options. It prints only; it never imports verl, starts Ray, downloads models, or runs training.

Boundaries

  • Dataset schema details, reward/tool internals, backend installation, and checkpoint merge/export operations belong to other verl sub-skills or repo-level references.
  • Do not point future agents at source checkout examples or scripts as runtime dependencies; adapt their patterns into commands or use the bundled script here.

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