Run a documented subset of verl v0.8 on-policy distillation on one consumer GPU. Bring a typed OPD profile and Parquet prompts, inspect rollout → teacher scoring → update locally, then export standard artifacts. miniVERL is independent; distributed execution and full verl compatibility are not claimed.
Install and run locally{ .md-button .md-button--primary } Read the compatibility boundary{ .md-button }
python -m pip install torch --index-url https://download.pytorch.org/whl/cu130
python -m pip install "miniverl[train,cuda]"
miniverl doctor
miniverl data sample --format verl-parquet --out prompts.parquet
miniverl plan --profile verl-opd-v0.8-single-gpu-v1 \
--config builtin:qwen3-0.6b-1.7b-opd \
--set 'data.train_files=["prompts.parquet"]'
miniverl run --profile verl-opd-v0.8-single-gpu-v1 \
--config builtin:qwen3-0.6b-1.7b-opd \
--set 'data.train_files=["prompts.parquet"]' --dry-runPlanning loads no weights. Remove --dry-run on one CUDA GPU to execute the
pinned Qwen3 recipe and export a standard PEFT adapter. Install the matching
CUDA-enabled PyTorch wheel first; the [cuda] extra does not select one.
For the exact maintainer-measured versions, use the
machine-readable known-good stack.
After inspection, write plan.json with plan --out, run it without
--dry-run, then use inspect, cache stats, export-verl and bridge doctor; the quickstart carries the complete copyable path.
miniVERL runs one local CPU process or one NVIDIA CUDA GPU. Fit depends on the model pair, context, kernels and VRAM; there is no GPU-name allowlist. Ray, FSDP, Megatron, PPO, GRPO and distributed launch are outside the runtime.
The executable profile pins verl v0.8.0 at 7aed6b23: one actor, one teacher,
n=1, GKD forward_kl_topk, token-mean and no reward/KL penalty. Unsupported
algorithm or distributed semantics fail closed. Exports remain unlaunchable
until exact base snapshots are materialized and checked under the pinned verl
commit. See scale-out materialization.
The v0.9 RTX 4080 developer workload consumed 32 distinct prompts and completed 8 current-policy updates at 3.1914 GiB peak reserved VRAM. Median steady-state rollout, teacher-scoring and update times were 9.7200, 0.4864 and 2.3260 seconds; a matched interruption/resume reproduced byte-identical trajectories, adapter and optimizer tensors. No quality endpoint or method comparison ran.
Measured workload evidence{ .md-button }
Plan, execute, inspect and resume one local pure-OPD run.
miniverl plan --profi
44D9
le verl-opd-v0.8-single-gpu-v1 --config verl-opd.yamlArtifact: a checksummed local execution plan, trajectories and PEFT adapter.
Next: Plan and run
Import the resolved, documented OPD subset with field-by-field classifications.
miniverl import-verl --profile verl-opd-v0.8-single-gpu-v1 \
--config verl-opd.yaml --out local-opd.yamlArtifact: a round-trippable profile and local-opd.import-report.json.
Next: Supported field boundary
Convert Parquet, export standard artifacts and inspect the unsupported boundary.
miniverl export-verl --run runs/my-opd --target-verl v0.8.0 --out scaleoutArtifact: PEFT + Parquet + OPD overrides and separate readiness flags.
The v0.7 external study stopped at its first preregistered gate: 0 selected checkpoints, 0 qualified teachers, 0 continuation arms and 0 final-test tasks accessed. All eight candidates scored 0/64 retained JSONNav utility against the unchanged 20% floor.
miniverl pilot --builtin-study alignment-external-v1 --jsonRead the early-stop study{ .md-button .md-button--primary }
Alignment Lab starts from a saturated SFT checkpoint. No continuation method improves it; measured regressions and unexecuted external safety endpoints stay visible. RecoveryBench and the calculator study likewise preserve their negative and mixed results rather than turning them into product claims.