unsloth/.github/workflows/notebooks-ci.yml
Daniel Han f3e541dd12 CI(notebooks): api-introspect installs unsloth from local checkout
The api-introspect job was pulling PyPI's `unsloth` via
`pip install --no-deps unsloth`. Latest released PyPI unsloth lacks
the CPU-torch fallback in unsloth/kernels/utils.py (lines 162-170)
that this branch carries, so `import unsloth` crashes with
AttributeError on `torch._C._cuda_getCurrentRawStream` (CPU torch
doesn't compile that symbol).

Switch to `pip install --no-deps -e ./unsloth` so the api-introspect
job validates the code in THIS PR head, not whatever's currently on
PyPI. unsloth_zoo continues to come from PyPI since the PR doesn't
modify unsloth_zoo.
2026-05-07 12:58:34 +00:00

362 lines
16 KiB
YAML

# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
#
# Cross-repo notebook validator. Lives in unslothai/unsloth (this repo)
# and inspects every notebook in unslothai/notebooks at HEAD (or the
# ref dispatched in via repository_dispatch).
#
# Catches the bug classes that landed in:
# - unslothai/notebooks#258 Colab torchao 0.10 vs peft 0.19 floor
# - unslothai/notebooks#260 DONT_UPDATE_EXCEPTIONS coverage drift
# - unslothai/notebooks#261 torch/torchcodec ABI; --no-deps tokenizers
# - unslothai/notebooks#264 --no-deps transformers + Colab tokenizers drift
# - unslothai/notebooks#221 git+ HEAD installs in install cells
# - unslothai/notebooks commit 51b1462 template/notebook drift
#
# CPU-only by design. Layer 2 (api-introspect) reuses the existing
# tests/_zoo_aggressive_cuda_spoof.py harness so `import unsloth`
# succeeds on a GPU-less ubuntu-latest runner.
name: Notebooks CI
on:
pull_request:
paths:
- 'unsloth/**'
- 'scripts/notebook_validator.py'
- 'scripts/notebook_to_python.py'
- 'scripts/data/colab_pip_freeze.gpu.txt'
- 'scripts/data/colab_to_cpu_pin.json'
- 'tests/notebooks/**'
- 'tests/_zoo_aggressive_cuda_spoof.py'
- '.github/workflows/notebooks-ci.yml'
schedule:
# Daily 06:17 UTC. Catches Colab preinstall bumps (the upstream image
# is rebuilt roughly weekly) without us waiting on a PR. Off the
# :00/:30 fleet-collision spots.
- cron: '17 6 * * *'
workflow_dispatch:
inputs:
notebooks_ref:
description: 'unslothai/notebooks ref to lint (branch / SHA / tag)'
default: 'main'
include_smoke:
description: 'Also run the install-cell smoke matrix (longer)'
type: boolean
default: false
repository_dispatch:
# Fired by a tiny companion workflow on unslothai/notebooks.
types: [notebooks_pr_opened, notebooks_main_pushed]
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions:
contents: read
env:
NOTEBOOKS_REF: >-
${{ github.event.inputs.notebooks_ref ||
github.event.client_payload.ref ||
'main' }}
jobs:
static:
name: static (drift + lint + exceptions)
runs-on: ubuntu-latest
timeout-minutes: 10
steps:
- name: Checkout unsloth (this PR)
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with:
path: unsloth
- name: Checkout unslothai/notebooks @ ${{ env.NOTEBOOKS_REF }}
uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with:
repository: unslothai/notebooks
ref: ${{ env.NOTEBOOKS_REF }}
path: notebooks
fetch-depth: 0 # drift check needs git status / diff
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
with:
python-version: '3.12'
cache: 'pip'
- name: Install validator deps
run: |
python -m pip install --upgrade pip
# nbformat + nbconvert come from the converter's requirements;
# spellchecker + huggingface_hub are imported at module top of
# update_all_notebooks.py.
pip install \
'nbformat>=5.10' 'nbconvert>=7.16' 'pyspellchecker>=0.8' \
'huggingface_hub>=0.34' 'tqdm>=4.66'
- name: Refresh Colab pip-freeze (best-effort; falls back to snapshot)
run: |
python unsloth/scripts/notebook_validator.py refresh-colab \
--out unsloth/scripts/data/colab_pip_freeze.gpu.txt \
|| echo "::warning::refresh-colab failed; using committed snapshot"
- name: Drift check (re-run update_all_notebooks.py + git diff)
working-directory: ${{ github.workspace }}
# Reported as non-blocking until the upstream `unslothai/notebooks`
# tree is regenerated. The first run on @main surfaces ~463 files
# of drift (7359 / 9634 line delta), which is a real backlog the
# notebooks-side maintainers need to clear in their own repo --
# this PR's role is to surface the count, not auto-fix it.
continue-on-error: true
run: |
python unsloth/scripts/notebook_validator.py drift \
--notebooks-dir notebooks
- name: Convert sanity (every nb / kaggle / original_template -> .py)
# Same rationale as Drift: a handful of upstream notebooks fail
# the converter (custom magics, malformed JSON, etc). Surface
# the count without blocking; the team triages in unslothai/notebooks.
continue-on-error: true
run: |
python unsloth/scripts/notebook_validator.py convert \
--notebooks-dir notebooks \
--out _converted
- name: Lint (install cells + AST scan, env-scoped)
# Reported as non-blocking (continue-on-error: true) until the
# backlog of pre-existing findings on unslothai/notebooks@main is
# cleared. Same pattern PR #5298 used for biome:check on the
# frontend. As of this commit the live tree surfaces 27 errors +
# 6 warnings, all real (peft/torchao floor missing in 6 nb/
# notebooks, 14 git+ HEAD installs in hand-tuned exception
# notebooks, 6 torch/torchcodec ABI mismatches, 1
# transformers/tokenizers --no-deps drift). The count surfaces
# in the PR check UI. Drop continue-on-error once it hits zero.
continue-on-error: true
run: |
python unsloth/scripts/notebook_validator.py lint \
--notebooks-dir notebooks \
--colab-pin unsloth/scripts/data/colab_pip_freeze.gpu.txt \
--no-pypi
# --no-pypi skips R-INST-002 (transitive resolve via PyPI metadata).
# Layer 1 keeps PR-time wall-clock predictable; the daily cron run
# below drops --no-pypi and refreshes the cache.
- name: DONT_UPDATE_EXCEPTIONS coverage
run: |
python unsloth/scripts/notebook_validator.py exceptions \
--notebooks-dir notebooks
static-with-pypi:
name: static + transitive resolve (cron / dispatch only)
if: ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
runs-on: ubuntu-latest
timeout-minutes: 15
steps:
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with: { path: unsloth }
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with:
repository: unslothai/notebooks
ref: ${{ env.NOTEBOOKS_REF }}
path: notebooks
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
with: { python-version: '3.12', cache: 'pip' }
- name: Install
run: pip install -U pip
- name: Refresh Colab oracle
run: |
python unsloth/scripts/notebook_validator.py refresh-colab \
--out unsloth/scripts/data/colab_pip_freeze.gpu.txt
- name: Lint with live PyPI metadata
run: |
python unsloth/scripts/notebook_validator.py lint \
--notebooks-dir notebooks \
--colab-pin unsloth/scripts/data/colab_pip_freeze.gpu.txt
api-introspect:
name: api surface (under CUDA spoof)
runs-on: ubuntu-latest
timeout-minutes: 12
steps:
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with: { path: unsloth }
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with:
repository: unslothai/notebooks
ref: ${{ env.NOTEBOOKS_REF }}
path: notebooks
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
with: { python-version: '3.12', cache: 'pip' }
- name: Install CPU torch + pinned unsloth + trl + converter deps
run: |
python -m pip install --upgrade pip
# CPU torch + torchvision. torchvision is required because
# unsloth_zoo.vision_utils imports PIL at module top, and the
# easiest way to get a torch-compatible PIL on a CPU runner is
# to let torchvision pull the right Pillow version.
pip install --index-url https://download.pytorch.org/whl/cpu \
'torch>=2.8,<2.11' 'torchvision<0.26'
# Pin to the same versions update_all_notebooks.py installs in
# generated notebooks. Keep these in lockstep with PIN_TRL /
# PIN_TRANSFORMERS in unslothai/notebooks/update_all_notebooks.py.
# `triton` is added because unsloth/_gpu_init.py:232 does an
# unconditional `import triton`; the PyPI wheel installs cleanly
# on Linux x86_64 even without CUDA (same rationale as
# consolidated-tests-ci.yml line 192-205).
# Pillow is listed explicitly as a defensive belt-and-braces
# next to torchvision (vision_utils crashes ModuleNotFoundError
# if torchvision skipped its Pillow dep for any reason).
pip install 'transformers>=4.56,<5.6' 'trl>=0.22,<0.26' 'accelerate>=1.0' \
'datasets>=3.4,<5' 'peft>=0.15,<0.20' \
'bitsandbytes>=0.43' 'sentencepiece' 'protobuf' triton \
Pillow safetensors tqdm packaging psutil
# Converter deps (nbformat for notebook_to_python.py).
pip install 'nbformat>=5.10' 'nbconvert>=7.16'
# Install unsloth from the LOCAL checkout (the PR head), not PyPI.
# The PR-time CI must validate the code in this PR; PyPI unsloth
# may lag the in-repo CPU-torch fallback in unsloth/kernels/utils.py
# (lines 162-170) that handles missing torch._C._cuda_getCurrentRawStream.
pip install --no-deps unsloth_zoo
pip install --no-deps -e ./unsloth
- name: Convert notebooks for AST scan
# Same upstream-conversion-error tolerance as the static job.
continue-on-error: true
run: |
python unsloth/scripts/notebook_validator.py convert \
--notebooks-dir notebooks --out _converted
- name: Dump unsloth + trl API surface (under CUDA spoof)
run: |
PYTHONPATH=unsloth/tests python -u - <<'PY'
import sys, json, inspect
import _zoo_aggressive_cuda_spoof as _spoof
_spoof.apply()
import unsloth
import trl
surface = {}
for cls_name in ("FastLanguageModel", "FastVisionModel", "FastModel"):
cls = getattr(unsloth, cls_name, None)
if cls is None:
continue
surface[cls_name] = sorted(n for n in dir(cls) if not n.startswith("_"))
surface["SFTConfig_kwargs"] = sorted(inspect.signature(trl.SFTConfig.__init__).parameters)
json.dump(surface, open("_api_surface.json", "w"), indent=2)
print("dumped surface for:", list(surface))
PY
- name: Run API rule against converted notebooks
run: |
python unsloth/scripts/notebook_validator.py api \
--converted-dir _converted \
--surface _api_surface.json
smoke-install:
name: smoke install (Colab-shaped venv, opt-in)
if: ${{ github.event.inputs.include_smoke == 'true' || github.event_name == 'schedule' }}
runs-on: ubuntu-latest
timeout-minutes: 25
strategy:
fail-fast: false
matrix:
# One representative notebook per installation_*_content template.
# Add rows when a new install template lands in update_all_notebooks.py.
notebook:
- 'nb/Llama3.1_(8B)-Alpaca.ipynb' # installation_content
- 'nb/Gemma3_(4B)-Vision.ipynb' # installation_content + vision
- 'nb/Llama3.1_(8B)-GRPO.ipynb' # installation_extra_grpo_content
- 'nb/gpt-oss-(20B)-Fine-tuning.ipynb' # installation_gpt_oss_content
- 'nb/Qwen3_5_(4B)_Vision.ipynb' # installation_qwen3_5_content
- 'nb/Nemotron-3-Nano-30B-A3B_A100.ipynb' # installation_nemotron_nano_content
- 'nb/Whisper.ipynb' # installation_whisper_content
- 'nb/Synthetic_Data_Hackathon.ipynb' # installation_synthetic_data_content
steps:
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with: { path: unsloth }
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
with:
repository: unslothai/notebooks
ref: ${{ env.NOTEBOOKS_REF }}
path: notebooks
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
with: { python-version: '3.12' }
- name: Seed Colab-shaped venv from pip-freeze (CPU-mapped)
run: |
# Strip cu128 local versions, route torch/torchvision to the CPU
# wheel index, drop CUDA-specific deps the runner can't use.
python -u - <<'PY' > /tmp/seed_pins.txt
import json, re
mapping = json.load(open("unsloth/scripts/data/colab_to_cpu_pin.json"))
rewrite = mapping["rewrite"]
skip = set(mapping["skip"])
spoof = set(mapping["module_spoof"])
out = []
for line in open("unsloth/scripts/data/colab_pip_freeze.gpu.txt"):
line = line.strip()
if not line or line.startswith("#"):
continue
m = re.match(r"^([A-Za-z0-9._-]+)\s*==\s*(.+)$", line)
if not m:
continue
name, ver = m.group(1).lower(), m.group(2)
if name in skip:
continue
if name in spoof:
continue
if name in rewrite:
ver = re.sub(r"[+\-].+$", "", ver)
out.append(f"{name}=={ver}")
else:
ver = re.sub(r"[+\-].+$", "", ver)
out.append(f"{name}=={ver}")
print("\n".join(out))
PY
head -5 /tmp/seed_pins.txt
wc -l /tmp/seed_pins.txt
- name: Install Colab-shaped venv
run: |
python -m pip install --upgrade pip
# Best-effort: any single line that fails to resolve on CPU is
# tolerated; the smoke contract is "the install cell + the unsloth
# import works", not "the entire Colab venv reproduces."
while IFS= read -r spec; do
pip install "$spec" --index-url https://download.pytorch.org/whl/cpu \
--extra-index-url https://pypi.org/simple || \
echo "::warning::pin failed: $spec"
done < /tmp/seed_pins.txt
- name: Run install cell
run: |
python unsloth/scripts/notebook_validator.py convert \
--notebooks-dir notebooks --out _converted
# Take the converted .py and run the install cell only.
BASE="$(basename '${{ matrix.notebook }}' .ipynb | tr -d '()' | tr -c '[:alnum:]_' _)"
PY="_converted/${BASE}.py"
[ -f "$PY" ] || { echo "::error::$PY not found"; ls _converted | head; exit 1; }
# Truncate at the first `from unsloth import` so we run install +
# core imports only.
awk '/^from unsloth import/ { print "import sys; sys.exit(0)"; exit } { print }' "$PY" > _smoke.py
PYTHONPATH=unsloth/tests python -u - <<'PY'
import _zoo_aggressive_cuda_spoof as _s; _s.apply()
# Stub torchcodec for cells that import it — no CPU wheel exists.
import sys, types
if "torchcodec" not in sys.modules:
sys.modules["torchcodec"] = types.ModuleType("torchcodec")
exec(open("_smoke.py").read(), {"__name__": "__main__"})
PY
- name: Verify imports under spoof
run: |
PYTHONPATH=unsloth/tests python -u - <<'PY'
import sys, types
if "torchcodec" not in sys.modules:
sys.modules["torchcodec"] = types.ModuleType("torchcodec")
import _zoo_aggressive_cuda_spoof as _s; _s.apply()
import unsloth, peft, torch, torchao, transformers, tokenizers
print("OK: imports pass under CUDA spoof")
PY