Clean up deprecated tile_tokens_dim for next flashinfer (#13341)
Signed-off-by: Vincent Zhong <207368749+vincentzed@users.noreply.github.com>
This commit is contained in:
@@ -1129,7 +1129,6 @@ class FlashInferFP4MoE(FusedMoE):
|
|||||||
local_expert_offset=self.moe_ep_rank * self.num_local_experts,
|
local_expert_offset=self.moe_ep_rank * self.num_local_experts,
|
||||||
local_num_experts=self.num_local_experts,
|
local_num_experts=self.num_local_experts,
|
||||||
routed_scaling_factor=self.moe_runner_config.routed_scaling_factor,
|
routed_scaling_factor=self.moe_runner_config.routed_scaling_factor,
|
||||||
tile_tokens_dim=None,
|
|
||||||
routing_method_type=RoutingMethodType.DeepSeekV3,
|
routing_method_type=RoutingMethodType.DeepSeekV3,
|
||||||
do_finalize=True,
|
do_finalize=True,
|
||||||
output=symm_output,
|
output=symm_output,
|
||||||
|
|||||||
@@ -1245,7 +1245,6 @@ class Fp8MoEMethod(FusedMoEMethodBase):
|
|||||||
routed_scaling_factor=(
|
routed_scaling_factor=(
|
||||||
routed_scaling_factor if routed_scaling_factor is not None else 1.0
|
routed_scaling_factor if routed_scaling_factor is not None else 1.0
|
||||||
),
|
),
|
||||||
tile_tokens_dim=None,
|
|
||||||
routing_method_type=routing_method_type,
|
routing_method_type=routing_method_type,
|
||||||
use_shuffled_weight=False,
|
use_shuffled_weight=False,
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -695,7 +695,6 @@ class ModelOptFp8MoEMethod(FusedMoEMethodBase):
|
|||||||
else 1.0
|
else 1.0
|
||||||
),
|
),
|
||||||
use_routing_scales_on_input=use_routing_scales_on_input,
|
use_routing_scales_on_input=use_routing_scales_on_input,
|
||||||
tile_tokens_dim=None,
|
|
||||||
routing_method_type=routing_method_type,
|
routing_method_type=routing_method_type,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|||||||
@@ -681,7 +681,6 @@ class Mxfp4MoEMethod(FusedMoEMethodBase):
|
|||||||
layer.moe_ep_rank * layer.num_local_experts, # local_expert_offset
|
layer.moe_ep_rank * layer.num_local_experts, # local_expert_offset
|
||||||
layer.num_local_experts, # local num experts
|
layer.num_local_experts, # local num experts
|
||||||
None,
|
None,
|
||||||
None, # tile_tokens_dim
|
|
||||||
1, # routing_method_type, renormalize
|
1, # routing_method_type, renormalize
|
||||||
True, # do finalize
|
True, # do finalize
|
||||||
output=symm_output,
|
output=symm_output,
|
||||||
|
|||||||
Reference in New Issue
Block a user