[EPLB] Simplify EPLB rearrange by only returning one map (#36267)

Signed-off-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Sage Moore
2026-03-18 20:34:00 -04:00
committed by GitHub
co-authored by Tyler Michael Smith
parent ef2c4f778d
commit c32a58cc2a
5 changed files with 197 additions and 160 deletions
+1 -15
View File
@@ -73,11 +73,7 @@ def run_rebalance_experts(
# Move the global expert load window to CPU for computation.
global_expert_load_window = eplb_stats.global_expert_load_window.cpu()
# Compute new expert mappings for the model
(
new_physical_to_logical_map,
new_logical_to_physical_map,
new_logical_replica_count,
) = eplb_state.policy.rebalance_experts(
new_physical_to_logical_map = eplb_state.policy.rebalance_experts(
global_expert_load_window,
eplb_stats.num_replicas,
eplb_stats.num_groups,
@@ -89,16 +85,6 @@ def run_rebalance_experts(
model_state.new_physical_to_logical_map = new_physical_to_logical_map
max_slots = model_state.logical_to_physical_map.shape[-1]
padded_logical = torch.nn.functional.pad(
new_logical_to_physical_map,
(0, max(0, max_slots - new_logical_to_physical_map.shape[-1])),
value=-1,
).to(model_state.logical_to_physical_map.device)
new_replica = new_logical_replica_count.to(model_state.logical_replica_count.device)
model_state.new_logical_to_physical_map = padded_logical
model_state.new_logical_replica_count = new_replica
async def transfer_run_periodically(
state: "EplbState",