Test 2: fix quantize_to_nvfp4 import
This commit is contained in:
@@ -45,7 +45,7 @@ def main():
|
||||
from dsv4.layers.grouped_linear import Nvfp4GroupedLinear
|
||||
from dsv4.layers.moe import Nvfp4MoE
|
||||
from dsv4.layers.shared_expert import Nvfp4SharedExpert
|
||||
from dsv4.ops.quantize import quantize_weight_to_nvfp4
|
||||
from dsv4.ops.quantize import quantize_weight_to_nvfp4, quantize_to_nvfp4
|
||||
|
||||
NUM_GPUS = 8
|
||||
PROMPT = "The capital of France is"
|
||||
|
||||
Reference in New Issue
Block a user