diff --git a/.github/workflows/triton-benchmarks.yml b/.github/workflows/triton-benchmarks.yml
index ac5735f727..8d975599f4 100644
--- a/.github/workflows/triton-benchmarks.yml
+++ b/.github/workflows/triton-benchmarks.yml
@@ -180,14 +180,6 @@ jobs:
           python ../../scripts/build_report.py $REPORTS/matmul-performance-at.csv $REPORTS/gemm-at-triton-report.csv --benchmark gemm-at --compiler triton --param_cols "B,M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
           python ../../scripts/build_report.py $REPORTS/matmul-performance-at.csv $REPORTS/gemm-at-onednn-report.csv --benchmark gemm-at --compiler onednn --param_cols "B,M,K,N" --tflops_col onednn-TFlops --hbm_col "onednn-GB/s" --tag $TAG
 
-      - name: Run Triton GEMM (stream-k) kernel benchmark
-        if: ${{ steps.install.outcome == 'success' && !cancelled() }}
-        run: |
-          cd benchmarks/triton_kernels_benchmark
-          python gemm_streamk_benchmark.py --reports $REPORTS
-          source ../../scripts/capture-hw-details.sh
-          python ../../scripts/build_report.py $REPORTS/matmul-streamk-performance.csv $REPORTS/gemm-streamk-triton-report.csv --benchmark gemm-streamk --compiler triton --param_cols "M,K,N" --tflops_col Triton-TFlops --hbm_col "Triton-GB/s" --tag $TAG
-
       - name: Run Triton GEMM (split-k) kernel benchmark
         if: ${{ steps.install.outcome == 'success' && !cancelled() }}
         run: |
diff --git a/third_party/intel/backend/compiler.py b/third_party/intel/backend/compiler.py
index 86948112b9..b10bb7d450 100644
--- a/third_party/intel/backend/compiler.py
+++ b/third_party/intel/backend/compiler.py
@@ -233,7 +233,7 @@ def make_ttgir(mod, metadata, opt, properties):
 
         passes.ttir.add_convert_to_ttgpuir(pm, "xpu", opt.num_warps, opt.threads_per_warp, opt.num_ctas)
         intel.passes.ttgpuir.add_accelerate_matmul(pm)
-        intel.passes.ttgpuir.add_remove_layout_conversions(pm)
+        ##        intel.passes.ttgpuir.add_remove_layout_conversions(pm)
         intel.passes.ttgpuir.add_materialize_block_pointer(pm)
         intel.passes.ttgpuir.add_rewrite_tensor_pointer(pm)
         intel.passes.ttgpuir.add_pipeline(pm, opt.num_stages, False)