diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
index 77a85160..b7bf9f5d 100644
--- a/.github/workflows/benchmark.yml
+++ b/.github/workflows/benchmark.yml
@@ -142,13 +142,13 @@ jobs:
     - name: Test tensor cores
       run: |
         NV=1 python3 test/test_linearizer.py TestLinearizer.test_tensor_cores TestLinearizer.test_tensor_cores_padded
-        PTX=1 python3 test/test_linearizer.py TestLinearizer.test_tensor_cores TestLinearizer.test_tensor_cores_padded
+        PTX=1 NV=1 python3 test/test_linearizer.py TestLinearizer.test_tensor_cores TestLinearizer.test_tensor_cores_padded
     - name: Run Tensor Core GEMM (CUDA)
       run: |
         CUDA=1 HALF=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul.txt
         CUDA=1 BFLOAT16=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul_bfloat16.txt
     - name: Run Tensor Core GEMM (PTX)
-      run: CUDA=1 PTX=1 HALF=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul_ptx.txt
+      run: NV=1 PTX=1 HALF=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul_ptx.txt
     - name: Run Tensor Core GEMM (NV)
       run: NV=1 HALF=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul_nv.txt
     - name: Run Tensor Core GEMM (NV) with BEAM
@@ -156,7 +156,7 @@ jobs:
     - name: Fuzz Padded Tensor Core GEMM (NV)
       run: NV=1 M_START=12 M_STOP=20 M_STEP=1 N_START=6 N_STOP=10 N_STEP=1 K_START=28 K_STOP=36 K_STEP=1 HALF=1 TC_OPT=2 python3 ./extra/gemm/fuzz_matmul.py
     - name: Fuzz Padded Tensor Core GEMM (PTX)
-      run: CUDA=1 PTX=1 M_START=12 M_STOP=20 M_STEP=1 N_START=6 N_STOP=10 N_STEP=1 K_START=28 K_STOP=36 K_STEP=1 HALF=1 TC_OPT=2 python3 ./extra/gemm/fuzz_matmul.py
+      run: NV=1 PTX=1 M_START=12 M_STOP=20 M_STEP=1 N_START=6 N_STOP=10 N_STEP=1 K_START=28 K_STOP=36 K_STEP=1 HALF=1 TC_OPT=2 python3 ./extra/gemm/fuzz_matmul.py
     - name: Run Stable Diffusion
       run: NV=1 THREEFRY=1 python3 examples/stable_diffusion.py --seed 0 --noshow --timing | tee sd.txt
     - name: Run SDXL