Skip to content

Advance development to 0.8.0.dev0 #57

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
DaoyuanLi2816 merged 1 commit into from
Aug 12, 2026
Merged

Advance development to 0.8.0.dev0 #57

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion PROJECT_STATE.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ and what it printed.

Last updated: 2026-08-11.

Canonical release state: releasing `v0.7.1`.
Canonical release state: stable `v0.7.1` (`830a4ca5d873bce4cdcc7c43a44d827b096e8c0c`), development `0.8.0.dev0`.
Every public version claim is generated from `release-state.yaml` and gated by
`python scripts/release_state.py --check`.

Expand Down
44 changes: 22 additions & 22 deletions PYPI.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
<p align="center">
<img src="https://raw.githubusercontent.com/DaoyuanLi2816/mini-verl/v0.7.1/docs/banner.svg" alt="miniVERL — single-GPU LLM post-training" width="880">
<img src="https://raw.githubusercontent.com/DaoyuanLi2816/mini-verl/main/docs/banner.svg" alt="miniVERL — single-GPU LLM post-training" width="880">
</p>

<div align="center">
Expand All @@ -8,15 +8,15 @@
[![Build](https://github.com/DaoyuanLi2816/mini-verl/actions/workflows/build.yml/badge.svg)](https://github.com/DaoyuanLi2816/mini-verl/actions/workflows/build.yml)
[![PyPI](https://img.shields.io/pypi/v/miniverl.svg)](https://pypi.org/project/miniverl/)
[![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12%20%7C%203.13-blue)](https://www.python.org)
[![License](https://img.shields.io/badge/license-Apache--2.0-blue)](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/LICENSE)
[![License](https://img.shields.io/badge/license-Apache--2.0-blue)](https://github.com/DaoyuanLi2816/mini-verl/blob/main/LICENSE)

</div>

<p align="center">
<a href="https://pypi.org/project/miniverl/"><strong>PyPI</strong></a> ·
<a href="https://daoyuanli2816.github.io/mini-verl/"><strong>Stable docs</strong></a> ·
<a href="https://daoyuanli2816.github.io/mini-verl/dev/">Development docs</a> ·
<a href="https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/README.zh-CN.md">中文</a>
<a href="https://github.com/DaoyuanLi2816/mini-verl/blob/main/README.zh-CN.md">中文</a>
</p>

**miniVERL is a local, inspectable single-GPU alignment and distillation
Expand Down Expand Up @@ -51,7 +51,7 @@ device-name agnostic, but fit depends on model pair, context, kernels and VRAM.
Install the matching CUDA-enabled PyTorch build first, then
`miniverl[train,cuda]`; that extra does not select a CUDA PyTorch wheel.
Ray, FSDP, Megatron, PPO, GRPO and distributed launch are outside the runtime.
See the [single-GPU guide](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/single-gpu-guide.md).
See the [single-GPU guide](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/single-gpu-guide.md).

## verl compatibility summary

Expand All @@ -66,7 +66,7 @@ Current exports remain `launchable: false`: the base snapshot is absent, the
reward scaffold fails closed and required mappings remain placeholders. The
entry point is `launch.template.sh`; readiness, parse/load evidence,
launchability, distributed execution and semantic parity are separate facts.
[Read the bridge contract](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/verl-bridge.md).
[Read the bridge contract](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/verl-bridge.md).

## One measured systems result

Expand All @@ -77,17 +77,17 @@ versus 3.035 GiB for dual model while running 10.1% slower. All 12
preregistered equivalence comparisons passed. This is one workload on one
machine, not a promise for other GPUs.

![Measured throughput and reserved VRAM for dual-model and shared-backbone runtime cells](https://raw.githubusercontent.com/DaoyuanLi2816/mini-verl/v0.7.1/docs/consumer-runtime-v1-pareto.svg)
![Measured throughput and reserved VRAM for dual-model and shared-backbone runtime cells](https://raw.githubusercontent.com/DaoyuanLi2816/mini-verl/main/docs/consumer-runtime-v1-pareto.svg)

[Consumer Runtime v1 methods and caveats](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/consumer-runtime-v1.md)
[Consumer Runtime v1 methods and caveats](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/consumer-runtime-v1.md)

## Three paths

| Path | Start with | Concrete artifact | Next |
| --- | --- | --- | --- |
| **Align** — use SFT, DPO, KD or OPD only when pilot evidence supports the cost | `miniverl pilot recipes/alignment_policy_conditioned_qwen.yaml` | `alignment-card.json` | [Alignment Lab](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/alignment-lab/alignment-lab-v1.md) |
| **Distill locally** — strict OPD, shared backbones and padded updates on one CUDA GPU | `miniverl train recipes/qwen_consumer_gpu_shared.yaml --dry-run` | resolved config and revision-pinned PEFT adapter | [Bring your own GPU](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/single-gpu-guide.md) |
| **Scale out** — convert Parquet, export standard artifacts and inspect the unsupported boundary | `miniverl bridge doctor scaleout-bundle` | `provenance/compatibility-report.json` | [Verified artifact bridge](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/verl-bridge.md) |
| **Align** — use SFT, DPO, KD or OPD only when pilot evidence supports the cost | `miniverl pilot recipes/alignment_policy_conditioned_qwen.yaml` | `alignment-card.json` | [Alignment Lab](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/alignment-lab/alignment-lab-v1.md) |
| **Distill locally** — strict OPD, shared backbones and padded updates on one CUDA GPU | `miniverl train recipes/qwen_consumer_gpu_shared.yaml --dry-run` | resolved config and revision-pinned PEFT adapter | [Bring your own GPU](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/single-gpu-guide.md) |
| **Scale out** — convert Parquet, export standard artifacts and inspect the unsupported boundary | `miniverl bridge doctor scaleout-bundle` | `provenance/compatibility-report.json` | [Verified artifact bridge](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/verl-bridge.md) |

## Research notes and preserved negative evidence

Expand All @@ -108,7 +108,7 @@ miniverl pilot --builtin-study alignment-external-v1 --json
The result is `do_not_continue_this_study` and `insufficient_evidence`, not a
recommendation among SFT/DPO/KD/OPD. Granite Guardian values are unqualified
selection diagnostics; Granite, PairRM and teacher qualification and the
reserved final test did not run. [Study and limitations](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/alignment-external/alignment-external-v1.md).
reserved final test did not run. [Study and limitations](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/alignment-external/alignment-external-v1.md).

### Earlier measured alignment case study

Expand All @@ -118,17 +118,17 @@ ceiling; continued SFT and both OPD variants retained measured regressions.
The two sandbox safety checks tied at zero while utility still regressed.
IFEval, XSTest, HarmBench and RewardBench were not executed, and “preference
win rate” is a deterministic Minipolicy paired outcome, not human preference.
[Seed-level evidence](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/alignment-lab/alignment-lab-v1.md).
[Seed-level evidence](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/alignment-lab/alignment-lab-v1.md).

- [RecoveryBench v1](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/recoverybench/recoverybench-v1.md): frozen-student KD
- [RecoveryBench v1](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/recoverybench/recoverybench-v1.md): frozen-student KD
beat slower fresh-state OPD on the preregistered primary view; the verifier
gate remained `insufficient_evidence`.
- [Calculator benchmark](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/benchmarking.md): both negative controls completed
- [Calculator benchmark](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/benchmarking.md): both negative controls completed
normally at 0%; the ambiguous historical protocol-v1 prompt prevents
attributing failure solely to intrinsic teacher behavior.
- [Limitations](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/limitations.md), [math](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/math.md),
[reproducibility](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/reproducibility.md) and
[compatibility policy](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/docs/compatibility.md).
- [Limitations](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/limitations.md), [math](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/math.md),
[reproducibility](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/reproducibility.md) and
[compatibility policy](https://github.com/DaoyuanLi2816/mini-verl/blob/main/docs/compatibility.md).

New runs establish tokenizer compatibility through structural identity. The
legacy behavioral fingerprint is only a migration fallback, not identity proof.
Expand All @@ -142,8 +142,8 @@ python -m pip install -e ".[dev]"
pytest -q -m "not gpu and not network"
```

Apache-2.0 licensed. See [CONTRIBUTING.md](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/CONTRIBUTING.md),
[SECURITY.md](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/SECURITY.md), the [changelog](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/CHANGELOG.md) and
[citation](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/CITATION.cff). Project records: [default GPU recipe](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/recipes/qwen_consumer_gpu_calc.yaml),
[frozen calculator result](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/benchmarks/results/gpu-calc-hard-equal-update-v2.json)
and [license](https://github.com/DaoyuanLi2816/mini-verl/blob/v0.7.1/LICENSE).
Apache-2.0 licensed. See [CONTRIBUTING.md](https://github.com/DaoyuanLi2816/mini-verl/blob/main/CONTRIBUTING.md),
[SECURITY.md](https://github.com/DaoyuanLi2816/mini-verl/blob/main/SECURITY.md), the [changelog](https://github.com/DaoyuanLi2816/mini-verl/blob/main/CHANGELOG.md) and
[citation](https://github.com/DaoyuanLi2816/mini-verl/blob/main/CITATION.cff). Project records: [default GPU recipe](https://github.com/DaoyuanLi2816/mini-verl/blob/main/recipes/qwen_consumer_gpu_calc.yaml),
[frozen calculator result](https://github.com/DaoyuanLi2816/mini-verl/blob/main/benchmarks/results/gpu-calc-hard-equal-update-v2.json)
and [license](https://github.com/DaoyuanLi2816/mini-verl/blob/main/LICENSE).
14 changes: 10 additions & 4 deletions docs/generated/quality.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"schema_version": 2,
"release": "0.7.1",
"status": "candidate",
"status": "released",
"quality_floor": "2,000+ tests and 85%+ branch coverage at v0.7.1",
"local_validation": {
"scope": "the maintainer's workstation, where the GPU and Windows-specific paths actually run",
Expand All @@ -28,9 +28,15 @@
},
"release_validation": {
"scope": "the exact published commit, validated by CI rather than locally",
"commit": "pending",
"workflows": {},
"conclusion": "pending",
"commit": "830a4ca5d873bce4cdcc7c43a44d827b096e8c0c",
"workflows": {
"ci": "https://github.com/DaoyuanLi2816/mini-verl/actions/runs/31566406949",
"build": "https://github.com/DaoyuanLi2816/mini-verl/actions/runs/31566406885",
"docs": "https://github.com/DaoyuanLi2816/mini-verl/actions/runs/31566406859",
"pinned_verl_bridge": "https://github.com/DaoyuanLi2816/mini-verl/actions/runs/31566406861",
"release": "https://github.com/DaoyuanLi2816/mini-verl/actions/runs/31566663507"
},
"conclusion": "success",
"gpu_coverage": "none; no GPU runner is configured for this repository, so the GPU counts above exist only from the local measurement"
}
}
4 changes: 2 additions & 2 deletions docs/overrides/main.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,12 @@
{% extends "base.html" %}

{% block announce %}
<div class="docs-channel" data-stable-version="0.7.1" data-dev-version="0.7.1">
<div class="docs-channel" data-stable-version="0.7.1" data-dev-version="0.8.0.dev0">
<strong id="docs-channel-label">Stable documentation</strong>
<label for="docs-version-selector">Version</label>
<select id="docs-version-selector" aria-label="Documentation version">
<option value="stable">Stable 0.7.1</option>
<option value="dev">Development 0.7.1</option>
<option value="dev">Development 0.8.0.dev0</option>
</select>
</div>
{% endblock %}
17 changes: 17 additions & 0 deletions docs/release-checklist.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,12 @@ This is the release gate and publication record for miniVERL. A checked item
names an invariant exercised on the stated source. Publication begins only
after the exact release commit and its remote checks are green.

## v0.8.0 single-GPU verl OPD pivot

- [ ] Implement and validate the documented verl v0.8 single-GPU OPD subset.
- [ ] Preserve every frozen benchmark and keep unsupported distributed semantics fail-closed.
- [ ] Complete the v0.8.0 release gates and public-distribution verification.

## v0.7.1 Product correction

- [x] README, Chinese README, PyPI description and docs landing page lead with
Expand Down Expand Up @@ -96,6 +102,17 @@ unauthorized after checkpoint-selection failure**.

## After the tag

- [x] v0.7.1 release run
[`31566663507`](https://github.com/DaoyuanLi2816/mini-verl/actions/runs/31566663507)
completed OIDC Trusted Publishing, attestation verification, exact clean
install and GitHub Release creation for commit
`830a4ca5d873bce4cdcc7c43a44d827b096e8c0c`.
- [x] PyPI and the GitHub Release expose identical v0.7.1 files: wheel SHA-256
`7d29669eaf53de0fd9b3056f3d00ad1d61c990fbe4f6cc97ccaf8e628c60e785`,
sdist SHA-256
`8131faee22e8b668bb0ff010f92ffafd9224aa046a017ad6f85fe7774301dea1`.
- [x] This separate state-sync PR advances main to `0.8.0.dev0` after v0.7.1.

- [x] Release run
[`31468663273`](https://github.com/DaoyuanLi2816/mini-verl/actions/runs/31468663273)
completed OIDC Trusted Publishing, attestation verification, exact clean
Expand Down
6 changes: 3 additions & 3 deletions release-state.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,13 +17,13 @@
# such distinction, which is how its tag shipped a docs selector still
# advertising "Stable 0.6.1 / Development 0.6.2.dev0".
schema_version: 1
phase: release
phase: development

stable:
version: "0.7.1"
tag: "v0.7.1"
release_commit: "pending"
release_commit: "830a4ca5d873bce4cdcc7c43a44d827b096e8c0c"
released_at: "2026-08-11"

development:
version: "0.7.1"
version: "0.8.0.dev0"
2 changes: 1 addition & 1 deletion src/miniverl/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,6 @@

from __future__ import annotations

__version__ = "0.7.1"
__version__ = "0.8.0.dev0"

__all__ = ["__version__"]