Enable modelopt gemma3 nvfp4/fp8, make workflow more robust (#22771)
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com> Signed-off-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
@@ -11,7 +11,8 @@ import pytest
|
||||
import torch
|
||||
|
||||
import vllm.model_executor.layers.fused_moe.modular_kernel as mk
|
||||
from vllm.config import VllmConfig, current_platform, set_current_vllm_config
|
||||
from vllm.config import VllmConfig, set_current_vllm_config
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.utils import has_deep_ep, has_deep_gemm, has_pplx
|
||||
from vllm.utils.flashinfer import has_flashinfer_cutlass_fused_moe
|
||||
|
||||
|
||||
Reference in New Issue
Block a user