Merge remote-tracking branch 'origin/main' into woa-nvidia-wsl-fallback

# Conflicts:
#	scripts/uninstall.sh
#	studio/setup.sh
This commit is contained in:
Daniel Han 2026-06-11 20:20:53 -07:00
commit 9bdd5436b2
234 changed files with 23233 additions and 3046 deletions

View file

@ -0,0 +1,289 @@
#!/usr/bin/env bash
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
#
# ──────────────────────────────────────────────────────────────────────────────
# Enable ROCm-on-WSL for AMD Strix Halo (Radeon 8060S / gfx1151)
# ──────────────────────────────────────────────────────────────────────────────
# install.sh already routes gfx1151 to the right ROCm wheels once a ROCm runtime
# is present; what it does NOT do is install AMD's ROCm userspace + the WSL DXG
# bridge. This helper automates that Linux-side prerequisite on Ubuntu 24.04
# WSL2 and is invoked by install.sh when it sees a Strix Halo APU in WSL (via
# /dev/dxg) but no ROCm runtime yet. Fully idempotent (re-run just re-verifies).
#
# Manual, admin-gated Windows prerequisite: an AMD Adrenalin driver with
# production ROCDXG/WSL support (26.2.2+). install.ps1 offers to update it. Once
# installed + rebooted, /dev/dxg is exposed to WSL and this script builds the rest.
#
# HOW ROCDXG WORKS (and why older /usr/lib/wsl/lib notes are wrong): librocdxg.so
# is AMD's user-mode bridge between the Linux HSA runtime and the Windows driver
# over /dev/dxg. The STANDARD hsa-rocr runtime (NOT the gone "roc4wsl" package)
# loads it when HSA_ENABLE_DXG_DETECTION=1. No hsa/rocm libs need injecting into
# /usr/lib/wsl/lib (it holds only d3d12/dxcore), yet rocminfo enumerates gfx1151
# fine -- so we gate on /dev/dxg, not on WSL lib injection.
#
# KNOWN CAVEAT (ROCm/ROCm#6022): librocdxg can cap usable ROCm VRAM at the WSL
# VM's RAM (.wslconfig [wsl2] memory=) on some BIOS UMA layouts, and amd-smi
# doesn't work in WSL. On OOM below capacity, raise memory= (then wsl --shutdown)
# and watch GPU use from Windows. Large-UMA BIOS exposes the full pool regardless.
#
# Verified on Ryzen AI Max+ PRO 395 / Radeon 8060S (gfx1151) with ROCm 7.2.1 +
# Ubuntu 24.04 + WSL2 + Adrenalin. These pins MOVE; bump + re-verify on newer ROCm.
# ──────────────────────────────────────────────────────────────────────────────
set -euo pipefail
# ── Tunables (override via env) ──────────────────────────────────────────────
ROCM_VER="${UNSLOTH_WSL_ROCM_VER:-7.2.1}" # ROCm release to install
GFX="gfx1151"
LIBROCDXG_REF="${UNSLOTH_LIBROCDXG_REF:-develop}" # ROCm/librocdxg git ref to build
# AMD's gfx1151 wheel index (same one install.sh uses); only for the smoke test.
TORCH_INDEX="${UNSLOTH_AMD_ROCM_MIRROR:-https://repo.amd.com/rocm/whl}/${GFX}/"
# Optional torch smoke test (throwaway venv). OFF by default: install.sh installs
# torch itself into the real venv right after, so a duplicate download is wasteful.
SMOKE_TEST="${UNSLOTH_WSL_SMOKE_TEST:-0}"
# REQUIRED constraint -- without it pip prefers PyPI's newer CUDA torch over the
# gfx1151 ROCm wheel. 2.11 carries AMD's real gfx1151 fix (matches install.sh).
TORCH_CONSTRAINT="${UNSLOTH_WSL_TORCH_CONSTRAINT:-torch>=2.11.0,<2.12.0}"
ROCM_DIR="" # resolved after install
say() { printf '\n\033[1;36m== %s\033[0m\n' "$*"; }
note() { printf ' %s\n' "$*"; }
die() { printf '\n\033[1;31m[BLOCKED] %s\033[0m\n' "$*" >&2; exit 1; }
# sudo only if not already root (WSL distros often run as root)
SUDO=""
if [ "$(id -u)" -ne 0 ]; then
command -v sudo >/dev/null 2>&1 || die "Need root or sudo to install ROCm."
SUDO="sudo"
fi
# ── Windows 11 SDK (headers for the librocdxg build) ─────────────────────────
# librocdxg's cmake build needs the Windows SDK 'shared' headers, which live on
# the Windows HOST under C:\Program Files (x86)\Windows Kits\10\Include\<ver>\.
_WIN_SDK_INC_BASE="/mnt/c/Program Files (x86)/Windows Kits/10/Include"
# Print the newest installed SDK include dir with 'shared' headers, or nothing.
# find + read loop (not `for ... in $(ls)`) since the base path has a space.
_find_win_sdk() {
[ -d "$_WIN_SDK_INC_BASE" ] || return 0
while IFS= read -r _inc; do
[ -n "$_inc" ] || continue
if [ -d "$_inc/shared" ]; then printf '%s' "$_inc"; return 0; fi
done < <(find "$_WIN_SDK_INC_BASE" -mindepth 1 -maxdepth 1 -type d 2>/dev/null | sort -Vr)
return 0
}
# Best-effort: install the Windows 11 SDK on the Windows HOST via winget so the
# build has its headers with no manual step. Elevates -> ONE UAC prompt; headers
# appear under /mnt/c immediately (no reboot). Never fatal -- failure falls
# through to a manual-install message. Opt out: UNSLOTH_SKIP_WIN_SDK_INSTALL=1.
_install_windows_sdk_via_winget() {
[ "${UNSLOTH_SKIP_WIN_SDK_INSTALL:-0}" = "1" ] && { note "Skipping Windows SDK auto-install (UNSLOTH_SKIP_WIN_SDK_INSTALL=1)."; return 0; }
command -v powershell.exe >/dev/null 2>&1 || return 0
# `command -v` succeeds even with WSL interop OFF (.exe on PATH but fails
# with "Exec format error"); verify it actually executes.
powershell.exe -NoProfile -Command "exit 0" >/dev/null 2>&1 || return 0
if ! powershell.exe -NoProfile -Command "if (Get-Command winget -ErrorAction SilentlyContinue) { exit 0 } else { exit 1 }" >/dev/null 2>&1; then
note "winget not available on the Windows host -- cannot auto-install the Windows SDK."
return 0
fi
say "Installing the Windows 11 SDK on the Windows host via winget"
note "librocdxg needs its headers. Approve the UAC prompt on the Windows desktop."
note "One-time (~1-3 GB download); opt out with UNSLOTH_SKIP_WIN_SDK_INSTALL=1."
# Newest SDK first, then a fallback. Header presence is the source of truth
# (re-check each attempt), not winget's exit code. </dev/null so winget never
# consumes a piped `curl | sh` stdin.
for _sdk_id in Microsoft.WindowsSDK.10.0.26100 Microsoft.WindowsSDK.10.0.22621; do
note "winget install ${_sdk_id} ..."
# --source winget: pin the community source so a broken default msstore
# source (the cert failure this PR fixes) can't abort SDK resolution.
powershell.exe -NoProfile -Command "winget install --id ${_sdk_id} -e --source winget --accept-source-agreements --accept-package-agreements --disable-interactivity" </dev/null || true
if [ -n "$(_find_win_sdk)" ]; then
note "Windows SDK headers present after install."
return 0
fi
done
note "Automatic Windows SDK install did not complete."
return 0
}
# ── PREFLIGHT ────────────────────────────────────────────────────────────────
say "Preflight checks"
# shellcheck disable=SC1091
. /etc/os-release 2>/dev/null || true
if [ "${VERSION_ID:-}" != "24.04" ]; then
die "This targets Ubuntu 24.04 (found '${VERSION_ID:-unknown}'). AMD's ROCm-on-WSL supports 24.04; create a dedicated distro: wsl --install Ubuntu-24.04 (do not run on 26.04 -- ROCm 7.2 does not target it yet)."
fi
if [ ! -e /dev/dxg ]; then
die "/dev/dxg missing -- WSL GPU paravirtualization not present. Ensure this is WSL2 (not WSL1) on a recent Windows build, and that an AMD GPU + ROCDXG-capable Adrenalin driver is installed on the Windows host (then reboot)."
fi
note "Ubuntu 24.04 + /dev/dxg present."
# Don't block on hsa/rocm libs in /usr/lib/wsl/lib: a working ROCDXG setup
# doesn't need them (only d3d12/dxcore). Real readiness is checked via rocminfo.
# ── Step 1: build/runtime prerequisites ──────────────────────────────────────
say "Installing build prerequisites"
export DEBIAN_FRONTEND=noninteractive
$SUDO apt-get update -y
# `make` is explicit: cmake shells out to it but Ubuntu only *recommends* it, so
# minimal images lack it and the librocdxg `make -j` build would fail.
$SUDO apt-get install -y cmake make gcc g++ git wget gpg ca-certificates python3-venv python3-pip
# ── Step 2: ROCm ${ROCM_VER} userspace (no DKMS -- WSL uses the Windows driver) ─
say "Installing ROCm ${ROCM_VER} userspace"
if ! command -v rocminfo >/dev/null 2>&1 && [ ! -x /opt/rocm/bin/rocminfo ]; then
# Direct apt-repo install (leaner than amdgpu-install; repo is indexed by
# ROCm version, e.g. .../apt/7.2.1).
$SUDO mkdir -p /etc/apt/keyrings
wget -qO- https://repo.radeon.com/rocm/rocm.gpg.key \
| gpg --dearmor | $SUDO tee /etc/apt/keyrings/rocm.gpg >/dev/null
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${ROCM_VER} noble main" \
| $SUDO tee /etc/apt/sources.list.d/rocm.list >/dev/null
printf 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600\n' \
| $SUDO tee /etc/apt/preferences.d/rocm-pin-600 >/dev/null
$SUDO apt-get update -y
# rocm-libs pulls everything torch links at runtime (rocblas, hipblas,
# miopen-hip, rccl, ...); hsa-rocr + rocminfo come as deps. Large (~5 GB
# download / ~23 GB installed).
$SUDO apt-get install -y rocm-libs rocminfo hip-runtime-amd
else
note "ROCm already present -- skipping apt install."
fi
# Resolve the real ROCm dir and ensure the canonical /opt/rocm symlink. apt lays
# ROCm under /opt/rocm-<ver> and rocm-core symlinks /opt/rocm -> that; repair if
# an earlier partial run left /opt/rocm as a real dir blocking the symlink.
_real="$(ls -d /opt/rocm-* 2>/dev/null | sort -V | tail -1 || true)"
if [ -n "$_real" ] && [ ! -L /opt/rocm ] && [ -d /opt/rocm ]; then
# /opt/rocm is a real dir blocking the symlink. Only treat it as a removable
# stray stub if it's NOT a real ROCm install (a real one has bin/rocminfo /
# bin/hipcc / .info/version) -- this protects a user's pre-existing ROCm. Even
# then we MOVE IT ASIDE, never rm -rf, so a wrong guess can't lose data.
if [ -e /opt/rocm/bin/rocminfo ] || [ -e /opt/rocm/bin/hipcc ] || [ -e /opt/rocm/.info/version ]; then
note "/opt/rocm is a real ROCm install -- leaving it untouched (will install librocdxg into it)."
else
note "Moving stray /opt/rocm stub aside -> $_real (not deleting it)"
$SUDO cp -an /opt/rocm/. "$_real"/ 2>/dev/null || true
$SUDO mv /opt/rocm "/opt/rocm.unsloth-stub-bak.$(date +%s)" 2>/dev/null || true
[ -e /opt/rocm ] || $SUDO ln -s "$_real" /opt/rocm
fi
elif [ -n "$_real" ] && [ ! -e /opt/rocm ]; then
$SUDO ln -s "$_real" /opt/rocm
fi
if [ -L /opt/rocm ] || [ -d /opt/rocm ]; then ROCM_DIR="/opt/rocm"; else ROCM_DIR="$_real"; fi
{ [ -n "$ROCM_DIR" ] && [ -d "$ROCM_DIR" ]; } || die "ROCm not found under /opt after install."
note "ROCm at ${ROCM_DIR}"
# ── Step 3: build librocdxg (DXG <-> HSA bridge; not yet an apt package) ──────
say "Building librocdxg (${LIBROCDXG_REF})"
if [ -e "${ROCM_DIR}/lib/librocdxg.so" ]; then
note "librocdxg already installed -- skipping build."
else
# Discover the newest installed Win11 SDK (version differs per machine). If
# absent, auto-install via winget (one UAC prompt) and re-discover; only if
# that ALSO fails do we stop with manual instructions.
_win_sdk="$(_find_win_sdk)"
if [ -z "$_win_sdk" ]; then
note "Windows 11 SDK headers not found -- attempting automatic install..."
_install_windows_sdk_via_winget
_win_sdk="$(_find_win_sdk)"
fi
[ -n "$_win_sdk" ] || die "Windows 11 SDK headers not found under 'C:\\Program Files (x86)\\Windows Kits\\10\\Include\\*\\shared', and the automatic winget install did not complete. Install it on the Windows host (e.g. 'winget install Microsoft.WindowsSDK.10.0.26100') and re-run."
note "Windows SDK: ${_win_sdk}"
_src="${HOME}/.unsloth/librocdxg"
rm -rf "$_src"
git clone --depth 1 --branch "$LIBROCDXG_REF" https://github.com/ROCm/librocdxg.git "$_src" \
|| git clone "https://github.com/ROCm/librocdxg.git" "$_src"
(
cd "$_src"
git checkout "$LIBROCDXG_REF" 2>/dev/null || true
mkdir -p build && cd build
cmake .. -DWIN_SDK="${_win_sdk}/shared"
make -j"$(nproc)"
$SUDO make install
)
fi
# Ensure soname symlinks resolve to whatever version was built (e.g. 1.2.0).
_dxg_real="$(ls -1 "${ROCM_DIR}"/lib/librocdxg.so.*.* 2>/dev/null | sort -V | tail -1 || true)"
if [ -n "$_dxg_real" ]; then
_dxg_base="$(basename "$_dxg_real")" # librocdxg.so.1.2.0
_dxg_major="$(printf '%s' "$_dxg_base" | sed -E 's/librocdxg\.so\.([0-9]+).*/\1/')"
$SUDO ln -sf "$_dxg_base" "${ROCM_DIR}/lib/librocdxg.so.${_dxg_major}"
$SUDO ln -sf "librocdxg.so.${_dxg_major}" "${ROCM_DIR}/lib/librocdxg.so"
fi
echo "${ROCM_DIR}/lib" | $SUDO tee /etc/ld.so.conf.d/rocm.conf >/dev/null
$SUDO ldconfig
# ── Step 4: persist environment (system-wide so Studio's worker inherits it) ──
say "Persisting ROCm-on-WSL environment"
_envfile="/etc/profile.d/unsloth-rocm-wsl.sh"
$SUDO tee "$_envfile" >/dev/null <<EOF
# >>> Unsloth ROCm-on-WSL (gfx1151) >>>
export HSA_ENABLE_DXG_DETECTION=1
export TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1
export PATH="${ROCM_DIR}/bin:\${PATH}"
export LD_LIBRARY_PATH="${ROCM_DIR}/lib:\${LD_LIBRARY_PATH:-}"
# <<< Unsloth ROCm-on-WSL (gfx1151) <<<
EOF
# also drop into ~/.bashrc for interactive shells
if [ -n "${HOME:-}" ] && ! grep -q "Unsloth ROCm-on-WSL" "${HOME}/.bashrc" 2>/dev/null; then
cat "$_envfile" >> "${HOME}/.bashrc"
fi
# export into the current process so verification below works immediately
export HSA_ENABLE_DXG_DETECTION=1
export PATH="${ROCM_DIR}/bin:${PATH}"
export LD_LIBRARY_PATH="${ROCM_DIR}/lib:${LD_LIBRARY_PATH:-}"
# ── Step 5: verify the runtime enumerates the GPU ────────────────────────────
say "Verifying rocminfo sees ${GFX}"
# Capture rocminfo into a var BEFORE grepping: piping into `grep -q` SIGPIPEs
# rocminfo on first match, which under `set -o pipefail` turns a successful match
# into a pipeline failure. Match the gfx1151 ISA "Name:" agent exactly (not a
# broad gfx1[0-9]) so a generic fallback ISA or unrelated RDNA GPU can't pass.
_rocminfo_out="$(rocminfo 2>/dev/null || true)"
if ! printf '%s\n' "$_rocminfo_out" | grep -qE "Name:[[:space:]]*${GFX}([^0-9]|$)"; then
printf '%s\n' "$_rocminfo_out" | head -25 >&2 || true
die "rocminfo did not enumerate a ${GFX} GPU agent. Most common cause: the Windows AMD driver predates production ROCDXG -- update Adrenalin (install.ps1 offers this), reboot, and re-run."
fi
# Display-only summary: best-effort (|| true) so head's early pipe-close under
# `set -o pipefail` can't fail the bootstrap after verification already passed.
printf '%s\n' "$_rocminfo_out" | grep -E 'Marketing Name|Device Type|Compute Unit' | grep -iE "Radeon|GPU|Compute" | head -3 || true
note "ROCm-on-WSL runtime is live for ${GFX}."
# ── Step 6 (optional): torch smoke test from the gfx1151 index ───────────────
if [ "$SMOKE_TEST" = "1" ]; then
say "Smoke-testing PyTorch on ${GFX} (throwaway venv)"
_venv="${HOME}/.unsloth/rocm-smoketest"
rm -rf "$_venv"; python3 -m venv "$_venv"
"$_venv/bin/pip" install --quiet --upgrade pip
# gfx1151 index is primary (torch + triton); PyPI only an extra for pure-py
# deps. The constraint keeps pip on the ROCm wheel, not a newer PyPI CUDA torch.
"$_venv/bin/pip" install --index-url "$TORCH_INDEX" \
--extra-index-url https://pypi.org/simple "$TORCH_CONSTRAINT" || \
die "torch install from ${TORCH_INDEX} failed."
"$_venv/bin/python" - <<'PY'
import torch
ok = torch.cuda.is_available()
print("torch:", torch.__version__, "| cuda(rocm) available:", ok)
if ok:
print("device:", torch.cuda.get_device_name(0))
free, total = torch.cuda.mem_get_info(0)
print(f"mem: free={free/1e9:.1f} GB total={total/1e9:.1f} GB")
import time
a = torch.randn(4096, 4096, device="cuda", dtype=torch.float16)
b = torch.randn(4096, 4096, device="cuda", dtype=torch.float16)
torch.cuda.synchronize(); t0 = time.time()
for _ in range(10): c = a @ b
torch.cuda.synchronize()
print(f"matmul ok ({(time.time()-t0)/10*1e3:.1f} ms/iter)")
raise SystemExit(0 if ok else 1)
PY
rm -rf "$_venv"
fi
say "Done."
note "ROCm-on-WSL is ready for ${GFX}. If you ran this standalone, install Unsloth"
note "in THIS distro and it will detect the GPU automatically:"
note " curl -fsSL https://unsloth.ai/install.sh | sh"

View file

@ -0,0 +1,143 @@
#!/usr/bin/env python3
"""Keep `allowScripts` pins in studio/frontend/package.json in sync with
package-lock.json.
`npm approve-scripts` writes version-pinned entries ("pkg@1.2.3": true).
A dependency bump strands the pin, so the approval (or denial) silently
stops matching and the package's install scripts fall back to
"unreviewed". This tool re-pins existing entries to the versions the
lockfile actually resolves; it never adds or removes entries, so
approving a brand-new script-bearing package stays a human decision.
Usage:
python scripts/sync_allow_scripts_pins.py --check # CI: exit 1 on drift
python scripts/sync_allow_scripts_pins.py --fix # rewrite package.json
Pinned keys follow npm's allowScripts grammar: "name@1.2.3" or
"name@1.2.3 || 1.2.4". Bare names (no version) match every version and
are left alone. Entries whose range is not an exact-version disjunction
(wildcards, tags) are left alone too.
"""
from __future__ import annotations
import argparse
import json
import re
import sys
from pathlib import Path
REPO_ROOT = Path(__file__).resolve().parents[1]
DEFAULT_DIR = REPO_ROOT / "studio" / "frontend"
EXACT_VERSION_RE = re.compile(r"^\d+\.\d+\.\d+(?:[-+][0-9A-Za-z.+-]+)?$")
def split_spec(key: str) -> tuple[str, str | None]:
"""'@scope/name@1.2.3' -> ('@scope/name', '1.2.3'); bare names -> (key, None)."""
if key.startswith("@"):
rest = key[1:]
if "@" not in rest:
return key, None
name, rng = rest.split("@", 1)
return "@" + name, rng
if "@" not in key:
return key, None
name, rng = key.split("@", 1)
return name, rng
def is_exact_disjunction(rng: str) -> bool:
parts = [p.strip() for p in rng.split("||")]
return all(EXACT_VERSION_RE.match(p) for p in parts) and bool(parts)
def version_sort_key(version: str) -> tuple:
release = version.split("-", 1)[0].split("+", 1)[0]
return tuple(int(x) for x in release.split(".")), version
def script_versions_from_lock(lock: dict) -> dict[str, list[str]]:
"""Map package name -> sorted versions that carry install scripts."""
out: dict[str, set[str]] = {}
for path, meta in (lock.get("packages") or {}).items():
if not path or not meta.get("hasInstallScript"):
continue
name = path.rsplit("node_modules/", 1)[-1]
version = meta.get("version")
if name and version:
out.setdefault(name, set()).add(version)
return {n: sorted(vs, key = version_sort_key) for n, vs in out.items()}
def desired_key(name: str, versions: list[str]) -> str:
return f"{name}@{' || '.join(versions)}"
def compute_renames(policy: dict, lock_versions: dict[str, list[str]]) -> dict[str, str]:
renames: dict[str, str] = {}
for key in policy:
name, rng = split_spec(key)
if rng is None or not is_exact_disjunction(rng):
continue # bare name or non-exact spec: matches by name, never stale
versions = lock_versions.get(name)
if not versions:
continue # package gone or script-free now: stale pin is inert
want = desired_key(name, versions)
if key != want:
renames[key] = want
return renames
def main(argv: list[str] | None = None) -> int:
ap = argparse.ArgumentParser(description = __doc__)
mode = ap.add_mutually_exclusive_group(required = True)
mode.add_argument("--check", action = "store_true", help = "exit 1 if pins are stale")
mode.add_argument("--fix", action = "store_true", help = "rewrite package.json in place")
ap.add_argument(
"--dir",
type = Path,
default = DEFAULT_DIR,
help = "directory holding package.json + package-lock.json",
)
args = ap.parse_args(argv)
pkg_path = args.dir / "package.json"
lock_path = args.dir / "package-lock.json"
if not pkg_path.exists() or not lock_path.exists():
print(f"sync-allow-scripts: nothing to do ({args.dir} has no package.json + lockfile)")
return 0
pkg = json.loads(pkg_path.read_text(encoding = "utf-8"))
policy = pkg.get("allowScripts")
if not isinstance(policy, dict) or not policy:
print("sync-allow-scripts: no allowScripts policy in package.json, nothing to do")
return 0
lock = json.loads(lock_path.read_text(encoding = "utf-8"))
renames = compute_renames(policy, script_versions_from_lock(lock))
if not renames:
print(f"sync-allow-scripts: {len(policy)} allowScripts entries in sync with the lockfile")
return 0
for old, new in renames.items():
print(f' stale pin: "{old}" -> "{new}"')
if args.check:
print(
"sync-allow-scripts: pins are stale; run "
"`python scripts/sync_allow_scripts_pins.py --fix` and commit the result"
)
return 1
pkg["allowScripts"] = {renames.get(k, k): v for k, v in policy.items()}
pkg_path.write_text(json.dumps(pkg, indent = 2, ensure_ascii = False) + "\n", encoding = "utf-8")
print(
f"sync-allow-scripts: re-pinned {len(renames)} entr{'y' if len(renames) == 1 else 'ies'} in {pkg_path}"
)
return 0
if __name__ == "__main__":
sys.exit(main())

View file

@ -16,15 +16,19 @@ function Uninstall-UnslothStudio {
function _Step { param([string]$Msg) Write-Host $Msg }
function _Substep { param([string]$Msg, [string]$Color = "Gray") Write-Host " $Msg" -ForegroundColor $Color }
# Remove a file/dir/symlink only if it exists. Idempotent.
# Remove a file/dir/symlink if present. Idempotent; retries since a just-killed
# process can briefly hold a handle (Windows refuses the delete until released).
function _RemovePath {
param([string]$Path)
if ([string]::IsNullOrWhiteSpace($Path)) { return }
if (Test-Path -LiteralPath $Path) {
if (-not (Test-Path -LiteralPath $Path)) { return }
for ($attempt = 1; $attempt -le 3; $attempt++) {
try {
Remove-Item -LiteralPath $Path -Recurse -Force -ErrorAction Stop
_Substep "removed: $Path" "Green"
return
} catch {
if ($attempt -lt 3) { Start-Sleep -Milliseconds 700; continue }
_Substep "could not remove: $Path ($($_.Exception.Message))" "Yellow"
}
}
@ -236,9 +240,58 @@ function Uninstall-UnslothStudio {
} catch { }
}
# Stop processes that would block deleting the paths we remove. Unlike
# _StopStudioProcesses (venv exe only), this also catches llama-server/llama-cli,
# the unsloth.exe shim, and orphaned mp workers under SYSTEM python holding a
# venv DLL (an open DLL handle blocks the dir delete) -- found by scanning each
# candidate's loaded modules, not just its image path.
function _StopProcessesLockingRoots {
param([string[]]$Roots)
$clean = @($Roots | Where-Object { $_ } | ForEach-Object { $_.TrimEnd('\','/') })
if ($clean.Count -eq 0) { return }
$underRoot = {
param($p)
if (-not $p) { return $false }
foreach ($r in $clean) { if ($p -ieq $r -or $p -ilike "$r\*") { return $true } }
return $false
}
# 1. Image path under a target root (venv python, shim, llama-server).
try {
foreach ($proc in (Get-CimInstance Win32_Process -ErrorAction SilentlyContinue)) {
if ((& $underRoot $proc.ExecutablePath)) {
try { Stop-Process -Id $proc.ProcessId -Force -ErrorAction SilentlyContinue } catch { }
}
}
} catch { }
# 2. A loaded module under a target root (orphaned mp-fork python holding a
# venv DLL). Scoped to names that load our DLLs to keep the scan fast.
try {
$cands = Get-Process -Name python, pythonw, unsloth, llama-server, llama-cli -ErrorAction SilentlyContinue
foreach ($proc in $cands) {
$hit = $false
try {
foreach ($m in $proc.Modules) { if ((& $underRoot $m.FileName)) { $hit = $true; break } }
} catch { } # access denied enumerating modules -> skip
if ($hit) { try { Stop-Process -Id $proc.Id -Force -ErrorAction SilentlyContinue } catch { } }
}
} catch { }
}
# Default install root + default data dir.
$defaultStudioHome = if ($env:USERPROFILE) { Join-Path $env:USERPROFILE ".unsloth\studio" } else { $null }
$defaultDataDir = if ($env:LOCALAPPDATA) { Join-Path $env:LOCALAPPDATA "Unsloth Studio" } else { $null }
# Default-mode ~/.unsloth holds a SHARED llama.cpp build + .cache that are
# siblings of studio (not under it), so deleting <studio> misses them -- handle
# explicitly. No-op in env/custom mode (nested under the custom root, removed
# with it). A user-set UNSLOTH_LLAMA_CPP_PATH is left alone.
$defaultUnslothHome = if ($env:USERPROFILE) { Join-Path $env:USERPROFILE ".unsloth" } else { $null }
$defaultLlamaCpp = if ($defaultUnslothHome) { Join-Path $defaultUnslothHome "llama.cpp" } else { $null }
$defaultCache = if ($defaultUnslothHome) { Join-Path $defaultUnslothHome ".cache" } else { $null }
# llama.cpp atomic-install staging root (install_llama_prebuilt.py .staging,
# sibling of the install dir). Usually pruned after activate, but an interrupted
# build can leave a "<name>.staging-XXXX" tree; removing it lets the empty-dir
# cleanup of ~/.unsloth below succeed. No-op in env/custom mode and when absent.
$defaultStaging = if ($defaultUnslothHome) { Join-Path $defaultUnslothHome ".staging" } else { $null }
# Build known-root list FIRST so the port-file kill can verify ownership.
$customRoots = @(_CustomStudioRoots)
@ -255,6 +308,9 @@ function Uninstall-UnslothStudio {
_StopByPortFile -PortFile (Join-Path $r "share\studio.port") -KnownRoots $knownRoots
}
_StopStudioProcesses -KnownRoots $knownRoots
# Also stop anything holding a handle on the exact paths we delete (llama-server,
# the CLI shim, an mp-fork python with a venv DLL) so the dir delete isn't refused.
_StopProcessesLockingRoots -Roots (@($knownRoots) + @($defaultDataDir, $defaultLlamaCpp, $defaultCache))
# ── Remove custom-root install trees ──
_Step "Removing data and install directories..."
@ -273,6 +329,16 @@ function Uninstall-UnslothStudio {
if ($defaultStudioHome) { _RemovePath $defaultStudioHome }
# Default data dir.
if ($defaultDataDir) { _RemovePath $defaultDataDir }
# Default-mode shared llama.cpp build + cache (siblings of studio under
# ~/.unsloth). No-op in env/custom mode and when absent.
if ($defaultLlamaCpp) { _RemovePath $defaultLlamaCpp }
if ($defaultCache) { _RemovePath $defaultCache }
if ($defaultStaging) { _RemovePath $defaultStaging }
# Drop ~/.unsloth itself, but ONLY if now empty -- never nuke unrelated content.
if ($defaultUnslothHome -and (Test-Path -LiteralPath $defaultUnslothHome) -and
-not (Get-ChildItem -LiteralPath $defaultUnslothHome -Force -ErrorAction SilentlyContinue)) {
_RemovePath $defaultUnslothHome
}
# ── Remove desktop and Start Menu shortcuts ──
_Step "Removing desktop and Start Menu shortcuts..."
@ -283,6 +349,18 @@ function Uninstall-UnslothStudio {
if ($env:APPDATA) {
_RemovePath (Join-Path $env:APPDATA "Microsoft\Windows\Start Menu\Programs\Unsloth Studio.lnk")
}
# Invalidate the Win11 Start Menu tile cache so the removed shortcut's tile
# disappears promptly instead of lingering stale (mirrors install.ps1's
# New-StudioShortcuts). Preserves start2.bin (the pin layout).
try {
$smehTemp = Join-Path $env:LOCALAPPDATA "Packages\Microsoft.Windows.StartMenuExperienceHost_cw5n1h2txyewy\TempState"
if (Test-Path -LiteralPath $smehTemp) {
Get-ChildItem -LiteralPath $smehTemp -Filter "TileCache_*" -ErrorAction SilentlyContinue |
Remove-Item -Force -ErrorAction SilentlyContinue
Remove-Item -LiteralPath (Join-Path $smehTemp "StartUnifiedTileModelCache.dat") -Force -ErrorAction SilentlyContinue
Stop-Process -Name StartMenuExperienceHost -Force -ErrorAction SilentlyContinue
}
} catch { }
# ── Clean user PATH and registry backup ──
_Step "Cleaning user PATH and registry..."

View file

@ -212,10 +212,24 @@ _custom_studio_roots | while IFS= read -r _custom_root; do
_remove_path "$_custom_root"
done
_remove_path "$HOME/.unsloth/studio"
# CUDA llama.cpp from provision_llama_cuda.sh (+ the fetched script). Clears the
# native-Linux build dir, or on WSL the symlink to the build install.ps1 removes.
# Default-mode shared llama.cpp build + cache are siblings of studio (not removed
# by deleting it). No-op in env/custom mode (they nest under the custom root) and
# when absent. A user-set UNSLOTH_LLAMA_CPP_PATH is intentionally kept.
_remove_path "$HOME/.unsloth/llama.cpp"
# provision_llama_cuda.sh fetched by the WoA/Spark CUDA-build path (install.ps1
# background build + direct-WSL setup.sh). No-op when absent.
_remove_path "$HOME/.unsloth/provision_llama_cuda.sh"
_remove_path "$HOME/.unsloth/.cache"
# llama.cpp atomic-install staging root (install_llama_prebuilt.py .staging).
# Normally pruned after activate, but an interrupted build can leave it behind;
# removing it lets the rmdir below succeed. No-op in env/custom mode and absent.
_remove_path "$HOME/.unsloth/.staging"
# ROCm-on-WSL helper artifacts (librocdxg build clone + smoke-test venv). No-op
# where they don't exist; removing them lets the rmdir below succeed.
_remove_path "$HOME/.unsloth/librocdxg"
_remove_path "$HOME/.unsloth/rocm-smoketest"
# Drop ~/.unsloth only if now empty (rmdir refuses non-empty, so user content is kept).
rmdir "$HOME/.unsloth" 2>/dev/null || true
_remove_path "$HOME/.local/share/unsloth"
# CLI shim: only the symlink Studio created, never a pip-installed file.
_remove_cli_shim
@ -248,22 +262,50 @@ case "$_os" in
Linux)
if [ "$_is_wsl" = "1" ]; then
echo "Removing WSL Windows-side shortcuts..."
# install.sh creates 'Unsloth Studio.lnk' on the Windows Desktop and
# Start Menu Programs folder via powershell.exe; mirror that path.
if command -v powershell.exe >/dev/null 2>&1; then
# install.sh creates per-distro 'Unsloth Studio (WSL - <distro>).lnk'
# on the Windows Desktop + Start Menu via powershell.exe. Scope removal
# to THIS distro (passed as $args[0]) so a multi-distro install keeps the
# other distros' launchers; the TARGET=wsl.exe check still spares a
# native install's "Unsloth Studio.lnk". Prefer powershell.exe; test it
# can EXECUTE (`command -v` succeeds even with interop OFF -- .exe then
# fails "Exec format error", common on systemd-enabled distros).
_wsl_distro="${WSL_DISTRO_NAME:-}"
_ps_ran=0
if command -v powershell.exe >/dev/null 2>&1 && \
powershell.exe -NoProfile -Command "exit 0" >/dev/null 2>&1; then
_ps_ran=1
# Inject the distro into the command: a -Command string does not
# receive trailing tokens as $args. WSL distro names are safe to
# embed (no quotes/$/backtick).
# shellcheck disable=SC2016
# $env:APPDATA is a PowerShell expansion; intentionally literal at shell level.
powershell.exe -NoProfile -Command '
# $env:APPDATA/$distro are PowerShell-side; $_wsl_distro is injected from shell.
powershell.exe -NoProfile -Command '$distro = "'"$_wsl_distro"'";
$dirs = @(
[Environment]::GetFolderPath("Desktop"),
(Join-Path $env:APPDATA "Microsoft\Windows\Start Menu\Programs")
);
$ws = New-Object -ComObject WScript.Shell;
foreach ($d in $dirs) {
if (-not $d) { continue }
$p = Join-Path $d "Unsloth Studio.lnk";
if (Test-Path -LiteralPath $p) { Remove-Item -LiteralPath $p -Force }
if (-not $d -or -not (Test-Path -LiteralPath $d)) { continue }
Get-ChildItem -LiteralPath $d -Filter "Unsloth Studio*.lnk" -ErrorAction SilentlyContinue | ForEach-Object {
try {
$sc = $ws.CreateShortcut($_.FullName);
if ("$($sc.TargetPath) $($sc.Arguments)" -notmatch "wsl\.exe") { return }
# When the distro is known, require the per-distro
# name for this distro or its -d "<distro>" argument
# so launchers for other distros are not removed.
if ($distro) {
$nameMatch = ($_.Name -eq "Unsloth Studio (WSL - $distro).lnk");
$argMatch = ($sc.Arguments -match ("-d\s+`"?" + [regex]::Escape($distro) + "`"?"));
if (-not ($nameMatch -or $argMatch)) { return }
}
Remove-Item -LiteralPath $_.FullName -Force -ErrorAction SilentlyContinue
} catch { }
}
}
# WSL-fallback native shim/launcher dir (%LOCALAPPDATA%\Unsloth) + its PATH entry.
# WoA WSL-fallback (install.ps1) native shim/launcher dir
# (%LOCALAPPDATA%\Unsloth) + its PATH entry. install.ps1 created the
# shim; clean it here too so a WSL-side bash uninstall is complete.
$ud = if ($env:LOCALAPPDATA) { Join-Path $env:LOCALAPPDATA "Unsloth" } else { $null };
if ($ud) {
$shim = (Join-Path $ud "bin").TrimEnd("\","/");
@ -272,6 +314,61 @@ case "$_os" in
if (Test-Path -LiteralPath $ud) { Remove-Item -LiteralPath $ud -Recurse -Force -ErrorAction SilentlyContinue }
}' >/dev/null 2>&1 || true
fi
# Fallback when powershell.exe can't run (interop disabled): remove the
# WSL .lnk files via drvfs. The "Unsloth Studio (WSL..." name is
# WSL-specific, so a native install's "Unsloth Studio.lnk" never matches.
if [ "$_ps_ran" = "0" ]; then
for _drive in /mnt/c /mnt/d /mnt/e; do
[ -d "$_drive/Users" ] || continue
for _udir in "$_drive"/Users/*; do
[ -d "$_udir" ] || continue
for _scdir in \
"$_udir/Desktop" \
"$_udir/OneDrive/Desktop" \
"$_udir"/OneDrive*/Desktop \
"$_udir/AppData/Roaming/Microsoft/Windows/Start Menu/Programs"; do
[ -d "$_scdir" ] || continue
if [ -n "$_wsl_distro" ]; then
# Exact per-distro name (no glob) so other distros survive.
_lnk="$_scdir/Unsloth Studio (WSL - ${_wsl_distro}).lnk"
[ -e "$_lnk" ] && rm -f "$_lnk" 2>/dev/null && echo " removed: $_lnk" || true
else
# Distro unknown: fall back to the broad WSL prefix.
for _lnk in "$_scdir"/"Unsloth Studio (WSL"*.lnk; do
[ -e "$_lnk" ] && rm -f "$_lnk" 2>/dev/null && echo " removed: $_lnk" || true
done
fi
done
done
done
fi
# ── ROCm-on-WSL config (install_rocm_wsl_strixhalo.sh) ──
# Remove Unsloth's own ROCDXG config (the env it persisted). The system
# ROCm userspace is a shared prereq (like CUDA) and is LEFT IN PLACE by
# default; set UNSLOTH_UNINSTALL_ROCM=1 to remove it too.
echo "Removing ROCm-on-WSL config..."
_sudo=""
if [ "$_uid" != "0" ] && command -v sudo >/dev/null 2>&1; then _sudo="sudo"; fi
$_sudo rm -f /etc/profile.d/unsloth-rocm-wsl.sh 2>/dev/null || true
if [ -f "$HOME/.bashrc" ] && grep -q "Unsloth ROCm-on-WSL" "$HOME/.bashrc" 2>/dev/null; then
_bk=$(mktemp 2>/dev/null || echo "$HOME/.bashrc.unsloth.tmp")
if sed '/# >>> Unsloth ROCm-on-WSL/,/# <<< Unsloth ROCm-on-WSL/d' "$HOME/.bashrc" > "$_bk" 2>/dev/null; then
cat "$_bk" > "$HOME/.bashrc" 2>/dev/null || true
echo " cleaned ROCm-on-WSL block from ~/.bashrc"
fi
rm -f "$_bk" 2>/dev/null || true
fi
if [ "${UNSLOTH_UNINSTALL_ROCM:-0}" = "1" ]; then
echo " removing system ROCm (UNSLOTH_UNINSTALL_ROCM=1)..."
$_sudo rm -f /etc/apt/sources.list.d/rocm.list /etc/apt/preferences.d/rocm-pin-600 \
/etc/apt/keyrings/rocm.gpg /etc/ld.so.conf.d/rocm.conf 2>/dev/null || true
$_sudo sh -c 'rm -rf /opt/rocm /opt/rocm-*' 2>/dev/null || true
if command -v ldconfig >/dev/null 2>&1; then $_sudo ldconfig 2>/dev/null || true; fi
elif [ -d /opt/rocm ]; then
echo " Note: ROCm userspace (/opt/rocm*) left in place (shared prereq)."
echo " Remove it by re-running with UNSLOTH_UNINSTALL_ROCM=1, or manually:"
echo " sudo rm -rf /opt/rocm /opt/rocm-* && sudo ldconfig"
fi
fi
echo "Removing Linux .desktop entry..."
_remove_path "$HOME/.local/share/applications/unsloth-studio.desktop"