[Docs] Reduce time spent generating API docs (#34255)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -680,6 +680,8 @@ class CompressedTensorsW4A4Nvfp4MoEMethod(CompressedTensorsMoEMethod):
|
||||
|
||||
|
||||
class CompressedTensorsW8A8Fp8MoEMethod(CompressedTensorsMoEMethod):
|
||||
"""W8A8 FP8 MoE quantization using compressed tensors."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
weight_quant: QuantizationArgs,
|
||||
|
||||
@@ -235,6 +235,8 @@ class Mxfp4Config(QuantizationConfig):
|
||||
|
||||
|
||||
class Mxfp4MoEMethod(FusedMoEMethodBase):
|
||||
"""MXFP4 MoE quantization method."""
|
||||
|
||||
def __init__(self, moe: FusedMoEConfig):
|
||||
super().__init__(moe)
|
||||
self.weight_dtype = "mxfp4"
|
||||
|
||||
Reference in New Issue
Block a user