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

studio: fix stale GGUF load-marker ordering test after inheritance relocation (#7252)

Browse source 
#6414 moved the llama_extra_args inheritance out of the GGUF branch in
_load_model_impl into _guard_chat_load_against_training, which runs before the
branch, so 'if request.llama_extra_args is None' is no longer inside the
gguf_branch slice that test_load_marker_precedes_hub_guard_and_unload checks.
The assertion failed on that now-missing landmark even though the guarantee it
protects (the gguf_load_in_flight marker is entered before the hub-download
guard and the unload) is intact. Drop the relocated landmark from the ordering
so the test matches the current structure.

Co-authored-by: danielhanchen <unslothshared@gmail.com>
This commit is contained in:
Daniel Han 2026-07-19 17:19:15 -07:00 • committed by GitHub
commit 17fd6c8ec6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 5 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

6
studio/backend/tests/test_gguf_load_cache_reuse.py
View file

@ -728,9 +728,13 @@ class TestLoadHubDownloadExclusion:
source = (Path(__file__).resolve().parent.parent / "routes" / "inference.py").read_text()
gguf_branch = source[source.index("if config.is_gguf:") :]
# The gguf_load_in_flight marker must be entered before the hub-download
# guard and the unload so a concurrent load can't race the download
# manager. The llama_extra_args inheritance that used to sit between the
# marker and the guard now runs in _guard_chat_load_against_training, ahead
# of the GGUF branch, so it is no longer a landmark inside this slice.
assert (
gguf_branch.index("enter_context(gguf_load_in_flight")
< gguf_branch.index("if request.llama_extra_args is None")
< gguf_branch.index("_hub_download_blocks_gguf_load")
< gguf_branch.index("unsloth_backend.unload_model")
)