[Optimization]1.fix tp+ep moe_forward; 2.set max_prefill_batch=env.MAX_PREFILL_NUM (#5353)

* [Optimization] 1.fix tp+ep moe_forward; 2.set max_prefill_batch=env.MAX_PREFILL_NUM

* fix test_chunked_moe

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

Author: carryyu

tests/distributed/chunked_moe.py

@@ -138,6 +138,7 @@ def setup_fused_moe(self):
         fused_moe = FusedMoE.__new__(FusedMoE)
         fused_moe.ep_size = 2
         fused_moe.tp_size = 1
+        fused_moe.attn_tp_size = 1
         fused_moe.reduce_results = True
 
         fused_moe.fd_config = mock_fd_config