[Perf][Feat] Add generic cuteDSL LL FP32 router (GEMM) (#44343)

Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

.buildkite/test_areas/kernels.yaml

@@ -230,8 +230,8 @@ steps:
 # Catch-all for test files at the tests/kernels root. This job collects
 # the whole root so new files are wired by default.
 # Files with dedicated jobs elsewhere in this file are excluded via --ignore
-# (test_bf16x3_router_gemm_cutedsl and test_ll_bf16_gemm run in their own jobs /
-# Kernels (B200)).
+# (test_bf16x3_router_gemm_cutedsl runs in Kernels (B200); test_ll_bf16_gemm and
+# test_ll_fp32w_gemm run in Gate Linear CuTeDSL Kernels (B200)).
 - label: ":nvidia: (B200) Miscellaneous Kernels"
   key: kernels-root-misc-test-b200
   timeout_in_minutes: 30
@@ -260,6 +260,7 @@ steps:
         --ignore=kernels/test_bf16x3_router_gemm_cutedsl.py
         --ignore=kernels/test_bf16x3_router_gemm_rocm.py
         --ignore=kernels/test_ll_bf16_gemm.py
+        --ignore=kernels/test_ll_fp32w_gemm.py
         --ignore=kernels/test_shuffle_rows.py
     # BROKEN on main, pending kernel fixes (B200):
     #   test_shuffle_rows.py (1: test_shuffle_rows_edge_cases)
@@ -595,9 +596,6 @@ steps:
   - vllm/v1/attention/backends/mla/flashinfer_mla.py
   - vllm/v1/attention/selector.py
   - vllm/platforms/cuda.py
-  - vllm/model_executor/kernels/linear/cute_dsl/ll_bf16.py
-  - vllm/model_executor/kernels/linear/cute_dsl/_ll_bf16_dotprod.py
-  - vllm/model_executor/kernels/linear/cute_dsl/_ll_bf16_splitk.py
   - vllm/cute_utils/
   - vllm/model_executor/layers/mamba/ops/gdn_chunk_cutedsl/
   - vllm/model_executor/layers/fused_moe/router/bf16x3_router_gemm_cutedsl.py
@@ -617,7 +615,6 @@ steps:
   - tests/kernels/test_fused_minimax_m3_qknorm_rope_kv_insert.py
   - tests/kernels/mamba/test_gdn_prefill_cutedsl.py
   - tests/kernels/test_bf16x3_router_gemm_cutedsl.py
-  - tests/kernels/test_ll_bf16_gemm.py
   - tests/kernels/test_top_k_per_row.py
   - tests/kernels/quantization/test_silu_mul_nvfp4_quant.py
   - tests/kernels/quantization/test_block_fp8.py
@@ -638,7 +635,6 @@ steps:
           pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
           pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
           pytest -v -s tests/kernels/test_bf16x3_router_gemm_cutedsl.py
-          pytest -v -s tests/kernels/test_ll_bf16_gemm.py
           ;;
         1)
           python3 examples/basic/offline_inference/chat.py
@@ -695,6 +691,28 @@ steps:
       - amd-smi
       - pytest -v -s kernels/quantization/test_nvfp4_emulation.py -k test_nvfp4_dense_emulation --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
 
+- label: ":nvidia: (B200) Gate Linear CuTeDSL Kernels"
+  key: kernels-gate-linear-cutedsl-b200
+  timeout_in_minutes: 15
+  working_dir: "/vllm-workspace/"
+  device: b200-k8s
+  source_file_dependencies:
+  - vllm/cute_utils/
+  - vllm/platforms/cuda.py
+  - vllm/model_executor/layers/fused_moe/router/gate_linear.py
+  - vllm/model_executor/kernels/linear/cute_dsl/_ll_router_common.py
+  - vllm/model_executor/kernels/linear/cute_dsl/ll_bf16.py
+  - vllm/model_executor/kernels/linear/cute_dsl/_ll_bf16_dotprod.py
+  - vllm/model_executor/kernels/linear/cute_dsl/_ll_bf16_splitk.py
+  - tests/kernels/test_ll_bf16_gemm.py
+  - vllm/model_executor/kernels/linear/cute_dsl/ll_fp32w.py
+  - vllm/model_executor/kernels/linear/cute_dsl/_ll_fp32w_dotprod.py
+  - tests/kernels/test_ll_fp32w_gemm.py
+  commands:
+    - nvidia-smi
+    - pytest -v -s tests/kernels/test_ll_bf16_gemm.py
+    - pytest -v -s tests/kernels/test_ll_fp32w_gemm.py
+
 - label: ":nvidia: (DGX) Spark b12x Linear Kernels Nightly"
   key: b12x-linear-kernels-dgx-spark-nightly
   timeout_in_minutes: 60