[Docs] improve code formatting and comments for eliminate griffe build warning. (vllm-project#25010)

Signed-off-by: samzong <samzong.lu@gmail.com>

Author: samzong

vllm/benchmarks/serve.py

@@ -139,7 +139,7 @@ async def get_request(
             A lower burstiness value (0 < burstiness < 1) results
             in more bursty requests, while a higher burstiness value
             (burstiness > 1) results in a more uniform arrival of requests.
-         ramp_up_strategy (optional):
+        ramp_up_strategy (optional):
             The ramp-up strategy. Can be "linear" or "exponential".
             If None, uses constant request rate (specified by request_rate).
         ramp_up_start_rps (optional):

vllm/distributed/eplb/eplb_state.py

@@ -337,11 +337,12 @@ def step(self,
         Args:
             model (MixtureOfExperts): The MoE model.
             is_dummy (bool): If `True`, this is a dummy step and the load
-                metrics recorded in this forward pass will not count. Defaults
-                to `False`.
+                metrics recorded in this forward pass will not count.
+                Defaults to `False`.
             is_profile (bool): If `True`, perform a dummy rearrangement
-                with maximum communication cost. This is used in `profile_run`
-                to reserve enough memory for the communication buffer.
+                with maximum communication cost. This is used in
+                `profile_run` to reserve enough memory
+                for the communication buffer.
             log_stats (bool): If `True`, log the expert load metrics.
 
         # Stats

vllm/distributed/eplb/rebalance_algo.py

@@ -109,13 +109,16 @@ def rebalance_experts_hierarchical(
         num_physical_experts: number of physical experts after replication
         num_groups: number of expert groups
         num_nodes: number of server nodes, where the intra-node network 
-            (e.g, NVLink) is faster
+            (e.g., NVLink) is faster
         num_gpus: number of GPUs, must be a multiple of `num_nodes`
 
     Returns:
-        physical_to_logical_map: [num_moe_layers, num_physical_experts]
-        logical_to_physical_map: [num_moe_layers, num_logical_experts, X]
-        logical_count: [num_moe_layers, num_logical_experts]
+        physical_to_logical_map (torch.Tensor):
+            [num_moe_layers, num_physical_experts]
+        logical_to_physical_map (torch.Tensor):
+            [num_moe_layers, num_logical_experts, X]
+        logical_count (torch.Tensor):
+            [num_moe_layers, num_logical_experts]
     """
     num_layers, num_logical_experts = weight.shape
     assert num_logical_experts % num_groups == 0
@@ -197,11 +200,13 @@ def rebalance_experts(
         num_gpus: number of GPUs, must be a multiple of `num_nodes`
 
     Returns:
-        physical_to_logical_map: [layers, num_replicas], the expert index of
-            each replica
-        logical_to_physical_map: [layers, num_logical_experts, X], the replica
-            indices for each expert
-        expert_count: [layers, num_logical_experts], number of physical
+        physical_to_logical_map:
+            [layers, num_replicas], the expert index of each replica
+        logical_to_physical_map:
+            [layers, num_logical_experts, X], the replica indices for each
+            expert
+        expert_count:
+            [layers, num_logical_experts], number of physical
             replicas for each logical expert
     """
     num_layers, num_logical_experts = weight.shape