[https://nvbugs/5619396][fix] Add sm103 to CutlassFP8RowwiseGemm (#9042)

Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>

Author: VALLIS-NERIA

cpp/tensorrt_llm/kernels/cutlass_kernels/fp8_rowwise_gemm/fp8_rowwise_gemm_template.h

@@ -686,7 +686,7 @@ size_t CutlassFp8RowwiseGemmRunner<T>::dispatchToArch(void* D, void const* A, vo
         return dispatchGemmToCutlassSm90<T>(D, A, B, C_bias, quantOption, m, n, k, scale_d0, scale_d1, gemmConfig,
             workspace, workspaceBytes, stream, occupancy);
     }
-    else if (mSm == 100)
+    else if (mSm == 100 || mSm == 103)
     {
         return dispatchGemmToCutlassSm100<T>(D, A, B, C_bias, quantOption, m, n, k, scale_d0, scale_d1, gemmConfig,
             workspace, workspaceBytes, stream, occupancy);
@@ -758,7 +758,7 @@ std::vector<tkc::CutlassGemmConfig> CutlassFp8RowwiseGemmRunner<T>::getConfigs()
             }
         }
     }
-    else if (mSm == 100)
+    else if (mSm == 100 || mSm == 103)
     {
         std::vector<tkc::CutlassTileConfigSM100> tilesSm100 = {
             tkc::CutlassTileConfigSM100::CtaShape64x32x128B,

tests/integration/test_lists/waives.txt

@@ -368,8 +368,6 @@ test_e2e.py::test_trtllm_serve_multimodal_example SKIP (https://nvbugs/5596377)
 unittest/llmapi/test_llm_multi_gpu_pytorch.py::test_llm_rpc_streaming_tp2 SKIP (https://nvbugs/5594753)
 triton_server/test_triton.py::test_cpp_unit_tests[cpp-unit-tests] SKIP (https://nvbugs/5619359)
 triton_server/test_triton_rcca.py::test_rcca_bug_4934893[Temperature:0.5-TOP_P:0.95-TOP_K:10-False-1---False-True-False-0-2048-enableDecoupleMode-inflight_fused_batching-disableTrtOverlap--max_utilization---1-1-1-False-ensemble] SKIP (https://nvbugs/5619369)
-unittest/_torch/thop/parallel/test_fp8_rowwise_linear.py::test_fp8_rowwise_linear[dtype0] SKIP (https://nvbugs/5619396)
-unittest/_torch/thop/parallel/test_fp8_rowwise_linear.py::test_fp8_rowwise_linear[dtype1] SKIP (https://nvbugs/5619396)
 accuracy/test_disaggregated_serving.py::TestQwen3_30B_A3B::test_mixed_ctx_gen_model[ctxpp2gentp2] SKIP (https://nvbugs/5582258)
 disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[llama-v3-8b-hf] SKIP (https://nvbugs/5587574)
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[throughput_tp8] SKIP (https://nvbugs/5629910)