ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix the CPU-only ROCm routing errors and two font-scale UI flakes (#7469)

Browse source 
* Fix the CPU-only ROCm routing errors and two font-scale UI flakes

Two unrelated causes of red CI on every PR, both reproduced before fixing.

ROCm routing: 12 errors on Repo tests (CPU). The spoof reports an AMD GPU, and
unsloth_zoo pulls in bitsandbytes, which picks a compute backend at import. Once
torch looks like a GPU is present, bnb loads its ROCm/CUDA ops, which a CPU-only
torch cannot satisfy (no libhipblas.so.2, no torch._C._cuda_getCurrentRawStream),
so the child died before printing RESULT. Nothing here tests bitsandbytes, so
import it first, under the honest hardware. Reproduced in a CPU-only torch venv:
11 passed with 12 errors before, 23 passed after. Still 23 passed on a CUDA build.

Font-scale UI: the select-viewport step pressed ArrowDown six times behind fixed
sleeps, but Radix moves focus into the listbox after the content opens, so on a
loaded runner the keys landed on the trigger and nothing scrolled. Wait on the
overflow and press until it moves, bounded at 40. The same fixed-sleep pattern
made open_appearance miss the dialog when the shortcut fired before the app wired
its handler; alternate both chords on a bounded retry and wait for the control the
caller is about to drive.

Both were reproduced locally by running the suite against a real Studio under full
CPU load. Original: 2 of 10 passed, with the exact CI signature 'keyboard did not
scroll the select viewport: 0' five times. Fixed: 10 of 10.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Keep the ROCm routing assertion live on Apple Silicon for PR #7469

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: danielhanchen <unslothai@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Daniel Han 2026-07-26 04:48:49 -07:00 • committed by GitHub
commit 170b412c1d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 79 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

16
tests/studio/install/test_rocm_rdna_routing.py
View file

@ -12,6 +12,7 @@ at import) resolves from a clean process.
from __future__ import annotations
import json
import os
import subprocess
import sys
from pathlib import Path
@ -43,6 +44,15 @@ _ARCHES = {
_CHILD = """
import json, sys
sys.path.insert(0, {tests!r})
# Import bitsandbytes under the real torch first. unsloth_zoo pulls it in, and it
# picks a compute backend at import: once the spoof reports an AMD GPU, it loads
# its ROCm/CUDA ops, which a CPU-only torch cannot satisfy (no libhipblas, no
# torch._C._cuda_getCurrentRawStream) and the child dies before printing RESULT.
# Nothing here tests bitsandbytes, so let it see the honest hardware.
try:
import bitsandbytes # noqa: F401
except Exception:
pass
import _zoo_rocm_spoof as spoof
arches = {arches!r}
spoof.apply(arches[0])
@ -60,7 +70,11 @@ print("RESULT " + json.dumps({{"device_type": device_type, "targets": targets}})
@pytest.fixture(scope = "module")
def routed():
code = _CHILD.format(tests = str(_TESTS_DIR), arches = list(_ARCHES))
proc = subprocess.run([sys.executable, "-c", code], capture_output = True, text = True)
# get_device_type() returns "mlx" before it ever looks at torch on Darwin arm64
# with mlx installed, so the spoof would be ignored. Force the GPU path to keep
# the assertion live there instead of skipping it.
env = {**os.environ, "UNSLOTH_FORCE_GPU_PATH": "1"}
proc = subprocess.run([sys.executable, "-c", code], capture_output = True, text = True, env = env)
line = next((l for l in proc.stdout.splitlines() if l.startswith("RESULT ")), None)
assert line, f"child produced no result.\nstdout:\n{proc.stdout}\nstderr:\n{proc.stderr}"
return json.loads(line[len("RESULT ") :])

101
tests/studio/playwright_ui_font_scale.py
View file

@ -16,6 +16,7 @@ import os
import sys
from pathlib import Path
from playwright.sync_api import TimeoutError as PWTimeout
from playwright.sync_api import sync_playwright
sys.path.insert(0, str(Path(__file__).resolve().parent))
@ -46,6 +47,18 @@ def near(
return a is not None and b is not None and abs(a - b) <= tol
_VP = 'document.querySelector("[data-radix-select-viewport]")'
SCROLL_TOP_JS = f"() => {_VP}.scrollTop"
SCROLLABLE_JS = f"() => {{ const vp = {_VP}; return !!vp && vp.scrollHeight > vp.clientHeight; }}"
VIEWPORT_STATE_JS = f"""
() => {{
const vp = {_VP};
return vp
? {{ scrollHeight: vp.scrollHeight, clientHeight: vp.clientHeight, top: vp.scrollTop }}
: null;
}}
"""
MEASURE_JS = """
() => {
const fs = (el) => (el ? parseFloat(getComputedStyle(el).fontSize) : null);
@ -83,15 +96,22 @@ def set_input(page, label, value):
def open_appearance(page):
page.keyboard.press("Control+,")
page.wait_for_timeout(700)
if page.get_by_role("dialog").count() == 0:
page.keyboard.press("Meta+,")
page.wait_for_timeout(700)
if page.get_by_role("dialog").count() == 0:
fail("settings dialog did not open")
page.get_by_role("dialog").get_by_role("button").filter(has_text = "Appearance").first.click()
page.wait_for_timeout(600)
# The shortcut can fire before the app has wired its key handler, so press
# each chord once behind a fixed sleep and a slow boot loses the dialog.
# Alternate them on a bounded retry, waiting on the dialog itself.
dialog = page.get_by_role("dialog")
for attempt in range(10):
page.keyboard.press("Meta+," if attempt % 2 else "Control+,")
try:
dialog.first.wait_for(state = "visible", timeout = 2_000)
break
except PWTimeout:
continue
if dialog.count() == 0:
fail("settings dialog did not open after 10 attempts")
dialog.get_by_role("button").filter(has_text = "Appearance").first.click()
# Wait for the control the caller is about to drive, not a fixed interval.
page.locator("input[aria-label='UI font size']").wait_for(state = "visible", timeout = 15_000)
def main():
@ -155,39 +175,46 @@ def main():
page.wait_for_timeout(400)
step("overflowing select scrolls its Radix viewport")
page.get_by_role("dialog").get_by_role("button").filter(has_text = "Voice").first.click()
page.wait_for_timeout(600)
voice = page.get_by_role("dialog").get_by_role("button").filter(has_text = "Voice").first
voice.click()
page.set_viewport_size({"width": 1440, "height": 480})
page.locator("[aria-label='Dictation language']").click()
page.wait_for_timeout(700)
state = page.evaluate(
"""
() => {
const vp = document.querySelector("[data-radix-select-viewport]");
return vp
? { scrollable: vp.scrollHeight > vp.clientHeight, top: vp.scrollTop }
: null;
}
"""
)
if not state or not state["scrollable"]:
fail(f"select viewport not scrollable: {state}")
for _ in range(6):
trigger = page.locator("[aria-label='Dictation language']")
trigger.wait_for(state = "visible")
trigger.click()
viewport = page.locator("[data-radix-select-viewport]")
viewport.wait_for(state = "visible")
# Wait for the overflow itself rather than a fixed sleep: the list is
# populated asynchronously, so measuring too early reads it as short.
try:
page.wait_for_function(SCROLLABLE_JS, timeout = 10_000)
except PWTimeout:
fail(f"select viewport not scrollable: {page.evaluate(VIEWPORT_STATE_JS)}")
# Radix moves focus into the listbox after the content opens, so a fixed
# burst of presses can land on the trigger and scroll nothing. Press until
# it moves instead; a real regression still fails, just after more tries.
kb_top = 0
for _ in range(40):
page.keyboard.press("ArrowDown")
page.wait_for_timeout(100)
kb_top = page.evaluate(
"() => document.querySelector('[data-radix-select-viewport]').scrollTop"
)
kb_top = page.evaluate(SCROLL_TOP_JS)
if kb_top > 0:
break
page.wait_for_timeout(50)
if not kb_top > 0:
fail(f"keyboard did not scroll the select viewport: {kb_top}")
vp_box = page.locator("[data-radix-select-viewport]").bounding_box()
fail(f"keyboard did not scroll the select viewport after 40 presses: {kb_top}")
vp_box = viewport.bounding_box()
page.mouse.move(vp_box["x"] + vp_box["width"] / 2, vp_box["y"] + 40)
page.mouse.wheel(0, -400)
page.wait_for_timeout(300)
wheel_top = page.evaluate(
"() => document.querySelector('[data-radix-select-viewport]').scrollTop"
)
if not wheel_top < kb_top:
try:
page.wait_for_function(
"top => document.querySelector('[data-radix-select-viewport]').scrollTop < top",
arg = kb_top,
timeout = 10_000,
)
except PWTimeout:
wheel_top = page.evaluate(SCROLL_TOP_JS)
fail(f"wheel did not scroll the select viewport: {kb_top} -> {wheel_top}")
page.keyboard.press("Escape")
page.set_viewport_size({"width": 1440, "height": 900})