[Rebase] Align vLLM-Omni with vLLM v0.31.0 (#8459)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
Zhou Taichang authored and GitHub committed 2026-10-05 14:11:01 +08:00
1 parent 1f47fa2f29
commit 0b0d2d7009
141 files changed
+2885 -721

No files matched your search

@@ -71,12 +71,12 @@ def _small_od_config(*, class_name=None):
def test_fp8_scope_and_prefix_propagation(monkeypatch):
from vllm.model_executor.layers.linear import LinearBase, UnquantizedLinearMethod
from vllm.model_executor.layers.quantization.fp8 import Fp8Config
from vllm.model_executor.layers.quantization.utils.quant_utils import (
is_layer_skipped,
)
from vllm_omni.diffusion.models.minimax_h3 import minimax_h3_transformer as h3
from vllm_omni.quantization.fp8_config import DiffusionFp8Config
monkeypatch.setattr(h3, "ColumnParallelLinear", _FakeLinear)
monkeypatch.setattr(h3, "MergedColumnParallelLinear", _FakeLinear)
@@ -92,7 +92,7 @@ def test_fp8_scope_and_prefix_propagation(monkeypatch):
"blocks.0.adaln_proj.linear",
"final_layer.adaln_proj.linear",
}
fp8_config = Fp8Config(ignored_layers=sorted(ignored_layers))
fp8_config = DiffusionFp8Config(ignored_layers=sorted(ignored_layers))
model = h3.MiniMaxH3DiTModel(
_small_od_config(),
quant_config=fp8_config,