update missing args

Author: zyongye

csrc/trtllm_batched_gemm_runner.cu

@@ -258,8 +258,9 @@ void TrtllmGenBatchedGemmRunner::run(
   // FIXME once we start using all-reduce in the epilogue of the bmm this can be moved elsewhere
   bmm.runInitBeforeWorldSync(config, gemmData, static_cast<void*>(stream));
 
-  auto const err = bmm.run(config, workspace, gemmData, static_cast<void*>(stream),
-                           multiProcessorCount, enable_pdl, globalTrtllmGenBatchedGemmModuleCache);
+  auto const err =
+      bmm.run(config, workspace, gemmData, static_cast<void*>(stream), multiProcessorCount,
+              enable_pdl, nullptr, globalTrtllmGenBatchedGemmModuleCache);
 
   FLASHINFER_CHECK(err == 0,
                    "Error occurred when running GEMM!"

csrc/trtllm_fused_moe_kernel_launcher.cu

@@ -1443,8 +1443,8 @@ class MxInt4BlockScaleLauncher : public FusedMoeLauncher {
         static_cast<int*>(num_tokens_per_expert.data_ptr()),
         static_cast<int*>(cta_idx_xy_to_batch_idx.data_ptr()),
         static_cast<int*>(cta_idx_xy_to_mn_limit.data_ptr()),
-        static_cast<int*>(num_non_exiting_ctas.data_ptr()), args->mDtypeElt, mRoutingBiasDtype,
-        use_routing_scales_on_input, use_deep_seek_fp8,
+        static_cast<int*>(num_non_exiting_ctas.data_ptr()), mDtypeScore, args->mDtypeElt,
+        mRoutingBiasDtype, use_routing_scales_on_input, use_deep_seek_fp8,
         static_cast<RoutingMethodType>(routing_method_type), routing_stream);
 
     check_moe();