Skip to content

del split func for fused_experts #4501

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
From00 merged 1 commit into from
May 21, 2026
+7 −61
Merged

del split func for fused_experts #4501

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 4 additions & 29 deletions paddleformers/transformers/glm_moe_dsa/modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,19 +122,12 @@ def _qkv_sep(matrix_2d, ortho_fn, kv_head_num=None, num_key_value_groups=None):
)

def _ffn_gate_up(matrix, ortho_fn, intermediate_size=None):
"""Slice FFN gate_up, orthogonalise gate and up independently."""
import paddle

if matrix.ndim == 2:
gate, up = paddle.split(matrix, [intermediate_size, intermediate_size], axis=1)
return paddle.concat([ortho_fn(gate), ortho_fn(up)], axis=1)
elif matrix.ndim == 3:
expert_updates = []
for ei in range(matrix.shape[0]):
gate, up = paddle.split(matrix[ei], [intermediate_size, intermediate_size], axis=1)
expert_updates.append(paddle.concat([ortho_fn(gate), ortho_fn(up)], axis=1))
return paddle.stack(expert_updates, axis=0)
else:
raise ValueError(f"FFN gate_up split expects 2D or 3D tensor, got shape {matrix.shape}")
assert matrix.ndim == 2 or matrix.ndim == 3, "FFN gate_up split expects 2D or 3D tensor"
gate, up = paddle.split(matrix, [intermediate_size, intermediate_size], axis=-1)
return paddle.concat([ortho_fn(gate), ortho_fn(up)], axis=-1)

def _mla_per_head(matrix_2d_global, ortho_fn, head_num=None, axis=None, head_split_sizes=None):
import paddle
Expand All @@ -144,17 +137,6 @@ def _mla_per_head(matrix_2d_global, ortho_fn, head_num=None, axis=None, head_spl
processed_groups = [ortho_fn(group) for group in groups]
return paddle.concat(processed_groups, axis=axis)

def _moe_experts(matrix_3d_global, ortho_fn):
import paddle

if matrix_3d_global.ndim != 3:
raise ValueError(f"MoE expert split expects 3D tensor, got shape {matrix_3d_global.shape}")
n_experts = matrix_3d_global.shape[0]
return paddle.stack(
[ortho_fn(matrix_3d_global[ei]) for ei in range(n_experts)],
axis=0,
)

slice_config = {}

muon_configs = config.muon_configs
Expand All @@ -164,7 +146,6 @@ def _moe_experts(matrix_3d_global, ortho_fn):
num_key_value_heads = config.num_key_value_heads
num_key_value_groups = num_attention_head // num_key_value_heads
use_mla = getattr(config, "q_lora_rank", None) and config.q_lora_rank > 0
moe_expert_fusion = getattr(config, "moe_expert_fusion", False)
use_gated_attn = getattr(config, "use_gated_attn", False)

muon_qkv_update_mode = muon_configs.get("muon_qkv_update_mode", "split_head")
Expand All @@ -181,8 +162,6 @@ def _moe_experts(matrix_3d_global, ortho_fn):

ffn_slice_fn = _ffn_gate_up if muon_ffn_split else None

fused_moe_fn = _moe_experts if moe_expert_fusion else None

mla_slice_fn = None
if use_mla and muon_qkv_update_mode == "split_head":
mla_slice_fn = _mla_per_head
Expand Down Expand Up @@ -216,10 +195,6 @@ def _add_layer_slice_config(prefix):
{"intermediate_size": moe_intermediate_size},
)

if moe_expert_fusion and fused_moe_fn is not None:
slice_config[f"{prefix}.mlp.experts.down_proj.weight"] = (fused_moe_fn, {})
slice_config[f"{prefix}.mlp.grouped_gemm_experts.weight2"] = (fused_moe_fn, {})

if use_mla and mla_slice_fn is not None:
assert (
hasattr(config, "qk_nope_head_dim")
Expand Down
35 changes: 3 additions & 32 deletions paddleformers/transformers/minimax_m2/modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,17 +93,9 @@ def _ffn_gate_up(matrix, ortho_fn, intermediate_size=None):
"""Slice FFN gate_up, orthogonalise gate and up independently."""
import paddle

if matrix.ndim == 2:
gate, up = paddle.split(matrix, [intermediate_size, intermediate_size], axis=1)
return paddle.concat([ortho_fn(gate), ortho_fn(up)], axis=1)
elif matrix.ndim == 3:
expert_updates = []
for ei in range(matrix.shape[0]):
gate, up = paddle.split(matrix[ei], [intermediate_size, intermediate_size], axis=1)
expert_updates.append(paddle.concat([ortho_fn(gate), ortho_fn(up)], axis=1))
return paddle.stack(expert_updates, axis=0)
else:
raise ValueError(f"FFN gate_up split expects 2D or 3D tensor, got shape {matrix.shape}")
assert matrix.ndim == 2 or matrix.ndim == 3, "FFN gate_up split expects 2D or 3D tensor"
gate, up = paddle.split(matrix, [intermediate_size, intermediate_size], axis=-1)
return paddle.concat([ortho_fn(gate), ortho_fn(up)], axis=-1)

def _mla_per_head(matrix_2d_global, ortho_fn, head_num=None, axis=None, head_split_sizes=None):
"""Slice MLA weights by heads."""
Expand All @@ -114,18 +106,6 @@ def _mla_per_head(matrix_2d_global, ortho_fn, head_num=None, axis=None, head_spl
processed_groups = [ortho_fn(group) for group in groups]
return paddle.concat(processed_groups, axis=axis)

def _moe_experts(matrix_3d_global, ortho_fn):
"""Slice MoE weights by experts."""
import paddle

if matrix_3d_global.ndim != 3:
raise ValueError(f"MoE expert split expects 3D tensor, got shape {matrix_3d_global.shape}")
n_experts = matrix_3d_global.shape[0]
return paddle.stack(
[ortho_fn(matrix_3d_global[ei]) for ei in range(n_experts)],
axis=0,
)

slice_config = {}

muon_configs = config.muon_configs
Expand All @@ -135,7 +115,6 @@ def _moe_experts(matrix_3d_global, ortho_fn):
num_key_value_heads = config.num_key_value_heads
num_key_value_groups = num_attention_head // num_key_value_heads
use_mla = getattr(config, "q_lora_rank", None) and config.q_lora_rank > 0
moe_expert_fusion = getattr(config, "moe_expert_fusion", False)
use_gated_attn = getattr(config, "use_gated_attn", False)

# Get Muon configuration from muon_configs
Expand All @@ -155,9 +134,6 @@ def _moe_experts(matrix_3d_global, ortho_fn):
# Determine FFN slice strategy
ffn_slice_fn = _ffn_gate_up if muon_ffn_split else None

# Determine Fused MoE slice strategy
fused_moe_fn = _moe_experts if moe_expert_fusion else None

# Determine MLA slice strategy
mla_slice_fn = None
if use_mla and muon_qkv_update_mode == "split_head":
Expand Down Expand Up @@ -198,11 +174,6 @@ def _add_layer_slice_config(prefix):
{"intermediate_size": moe_intermediate_size},
)

# Fused MoE weights (grouped_gemm)
if moe_expert_fusion and fused_moe_fn is not None:
slice_config[f"{prefix}.mlp.experts.down_proj.weight"] = (fused_moe_fn, {})
slice_config[f"{prefix}.mlp.grouped_gemm_experts.weight2"] = (fused_moe_fn, {})

# MLA weights
if use_mla and mla_slice_fn is not None:
assert (
Expand Down
Loading