From fbc93a0e08e44bd92d68c8c12617642f47448990 Mon Sep 17 00:00:00 2001 From: WeiQing Chen <40507679+david6666666@users.noreply.github.com> Date: Sat, 29 Aug 2026 12:11:31 +0800 Subject: [PATCH] [ci][bugfix] Fix MiniMax-H3 FP8 quality test OOM (#6742) Signed-off-by: david6666666 <530634352@qq.com> Co-authored-by: OpenAI Codex --- .../models/minimax_h3/test_minimax_h3_quantization_quality.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tests/diffusion/models/minimax_h3/test_minimax_h3_quantization_quality.py b/tests/diffusion/models/minimax_h3/test_minimax_h3_quantization_quality.py index 5d8c0fa25..0fb043a1e 100644 --- a/tests/diffusion/models/minimax_h3/test_minimax_h3_quantization_quality.py +++ b/tests/diffusion/models/minimax_h3/test_minimax_h3_quantization_quality.py @@ -1,5 +1,5 @@ # SPDX-License-Identifier: Apache-2.0 -# SPDX-FileCopyrightText: Copyright contributors to the vLLM project +# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project from pathlib import Path @@ -187,6 +187,8 @@ def test_minimax_h3_quantization_quality(config: QualityTestConfig): "model": model_ref, "enforce_eager": True, "tensor_parallel_size": 2, + # The fused BF16 baseline only fits on H100-80GB with encoder TP. + "text_encoder_tp_size": 2, "vae_use_tiling": True, }