biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Relax Transformers modeling backend MoE experts check (#28952)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-11-19 14:50:30 +01:00
committed by GitHub
parent 09540cd918
commit 4f5299f717
2 changed files with 11 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
vllm/model_executor/models/transformers/moe.py
View File

@@ -256,7 +256,14 @@ class MoEMixin(MixtureOfExperts):
def _recursive_replace(module: nn.Module, prefix: str):
for child_name, child_module in module.named_children():
qual_name = maybe_prefix(prefix, child_name)
if child_name == "experts" and isinstance(child_module, nn.ModuleList):
# Naive implementations will have experts as ModuleList
is_modulelist = isinstance(child_module, nn.ModuleList)
# Packed implementations will have experts as 3D tensors of shapes like:
# gate_up_proj = (num_experts, 2 * intermediate_size, hidden_size)
# down_proj = (num_experts, intermediate_size, hidden_size)
params = list(child_module.parameters())
is_3d = len(params) > 0 and all(p.ndim == 3 for p in params)
if child_name == "experts" and (is_modulelist or is_3d):
# Alias for readability
mlp = module
experts = child_module