From 17fd6c8ec6c3788c1da2f9e86452fc340e451444 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Sun, 19 Jul 2026 17:19:15 -0700 Subject: [PATCH] studio: fix stale GGUF load-marker ordering test after inheritance relocation (#7252) #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 --- studio/backend/tests/test_gguf_load_cache_reuse.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/studio/backend/tests/test_gguf_load_cache_reuse.py b/studio/backend/tests/test_gguf_load_cache_reuse.py index 15d91cd324..62596fcc8a 100644 --- a/studio/backend/tests/test_gguf_load_cache_reuse.py +++ b/studio/backend/tests/test_gguf_load_cache_reuse.py @@ -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") )