From f1414a226d7f107d8e66046e7be49c76afe82b61 Mon Sep 17 00:00:00 2001 From: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com> Date: Fri, 7 Aug 2026 04:42:16 -0700 Subject: [PATCH] Give the EAGLE-3 cp_size=2 compile case a longer timeout test_llama_eagle3[2-False] timed out at the 300s examples default in the first nightly after #2086 re-enabled the cp_size=2 cases, which the old version guard had skipped since February. Measured on the 2-GPU runner: [2-False] 304s, [1-False] 173s, [2-True] 51s, [1-True] 39s. Only [2-False] exceeds the default, and only by 4s: it pays context parallelism plus torch.compile, which mix_hidden_states=False enables. The marker is scoped to that one case so the 300s cap keeps protecting the rest. Co-Authored-By: Claude Opus 5 Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com> --- tests/examples/speculative_decoding/test_eagle.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tests/examples/speculative_decoding/test_eagle.py b/tests/examples/speculative_decoding/test_eagle.py index 0decc6b03d0..8d284d4ba1b 100644 --- a/tests/examples/speculative_decoding/test_eagle.py +++ b/tests/examples/speculative_decoding/test_eagle.py @@ -116,7 +116,12 @@ def test_calibrate_draft_vocab(tiny_llama_path, tiny_daring_anteater_path, draft # fmt: off -@pytest.mark.parametrize(("cp_size", "mix_hidden_states"), [(1, False), (2, False), (1, True), (2, True)]) +@pytest.mark.parametrize(("cp_size", "mix_hidden_states"), [ + (1, False), + pytest.param(2, False, marks=pytest.mark.timeout(360)), + (1, True), + (2, True), +]) def test_llama_eagle3(tiny_llama_path, tiny_daring_anteater_path, eagle_output_dir,