diff --git a/.github/scripts/defaults.sh b/.github/scripts/defaults.sh
index 1f0310fe..1c1b7def 100755
--- a/.github/scripts/defaults.sh
+++ b/.github/scripts/defaults.sh
@@ -30,7 +30,7 @@ REMOTE_COURSIER_CACHE=$REMOTE_WORK_DIR/.coursier-cache
 declare -A grouping
 grouping["group-cores"]="chipyard-cva6 chipyard-ibex chipyard-rocket chipyard-hetero chipyard-boom chipyard-sodor chipyard-digitaltop chipyard-multiclock-rocket chipyard-nomem-scratchpad chipyard-spike chipyard-clone"
 grouping["group-peripherals"]="chipyard-dmirocket chipyard-dmiboom chipyard-spiflashwrite chipyard-mmios chipyard-nocores chipyard-manyperipherals chipyard-chiplike"
-grouping["group-accels"]="chipyard-mempress chipyard-sha3 chipyard-hwacha chipyard-gemmini chipyard-manymmioaccels"
+grouping["group-accels"]="chipyard-mempress chipyard-sha3 chipyard-hwacha chipyard-gemmini chipyard-manymmioaccels chipyard-nvdla"
 grouping["group-constellation"]="chipyard-constellation"
 grouping["group-tracegen"]="tracegen tracegen-boom"
 grouping["group-other"]="icenet testchipip constellation rocketchip-amba rocketchip-tlsimple rocketchip-tlwidth rocketchip-tlxbar"
@@ -44,6 +44,7 @@ mapping["chipyard-sha3"]=" CONFIG=Sha3RocketConfig"
 mapping["chipyard-mempress"]=" CONFIG=MempressRocketConfig"
 mapping["chipyard-digitaltop"]=" TOP=DigitalTop"
 mapping["chipyard-manymmioaccels"]=" CONFIG=ManyMMIOAcceleratorRocketConfig"
+mapping["chipyard-nvdla"]=" CONFIG=SmallNVDLARocketConfig"
 mapping["chipyard-hetero"]=" CONFIG=LargeBoomAndRocketConfig"
 mapping["chipyard-boom"]=" CONFIG=MediumBoomCosimConfig"
 mapping["chipyard-dmiboom"]=" CONFIG=dmiMediumBoomCosimConfig"
diff --git a/.github/scripts/run-tests.sh b/.github/scripts/run-tests.sh
index 798bad0d..4a5a0802 100755
--- a/.github/scripts/run-tests.sh
+++ b/.github/scripts/run-tests.sh
@@ -87,12 +87,14 @@ case $1 in
 	# test streaming-fir
         make -C $LOCAL_SIM_DIR $DISABLE_SIM_PREREQ ${mapping[$1]} run-binary-fast BINARY=$LOCAL_CHIPYARD_DIR/tests/streaming-fir.riscv
 
-	# test nvdla
-        make -C $LOCAL_SIM_DIR $DISABLE_SIM_PREREQ ${mapping[$1]} BINARY=$LOCAL_CHIPYARD_DIR/tests/nvdla.riscv run-binary-fast
-
 	# test fft
         make -C $LOCAL_SIM_DIR $DISABLE_SIM_PREREQ ${mapping[$1]} BINARY=$LOCAL_CHIPYARD_DIR/tests/fft.riscv run-binary-fast
+	;;
+    chipyard-nvdla)
+	make -C $LOCAL_CHIPYARD_DIR/tests
 
+	# test nvdla
+        make -C $LOCAL_SIM_DIR $DISABLE_SIM_PREREQ ${mapping[$1]} BINARY=$LOCAL_CHIPYARD_DIR/tests/nvdla.riscv run-binary-fast
 	;;
     chipyard-manyperipherals)
 	# SPI Flash read tests, then bmark tests
diff --git a/.github/workflows/chipyard-run-tests.yml b/.github/workflows/chipyard-run-tests.yml
index fecf7976..02de6935 100644
--- a/.github/workflows/chipyard-run-tests.yml
+++ b/.github/workflows/chipyard-run-tests.yml
@@ -741,6 +741,29 @@ jobs:
           group-key: "group-accels"
           project-key: "chipyard-manymmioaccels"
 
+  chipyard-nvdla-run-tests:
+    name: chipyard-nvdla-run-tests
+    needs: prepare-chipyard-accels
+    runs-on: self-hosted
+    steps:
+      - name: Delete old checkout
+        run: |
+            ls -alh .
+            rm -rf ${{ github.workspace }}/* || true
+            rm -rf ${{ github.workspace }}/.* || true
+            ls -alh .
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Git workaround
+        uses: ./.github/actions/git-workaround
+      - name: Create conda env
+        uses: ./.github/actions/create-conda-env
+      - name: Run tests
+        uses: ./.github/actions/run-tests
+        with:
+          group-key: "group-accels"
+          project-key: "chipyard-nvdla"
+
   chipyard-mempress-run-tests:
     name: chipyard-mempress-run-tests
     needs: prepare-chipyard-accels
@@ -1013,6 +1036,7 @@ jobs:
             chipyard-sha3-run-tests,
             chipyard-gemmini-run-tests,
             chipyard-manymmioaccels-run-tests,
+            chipyard-nvdla-run-tests,
             chipyard-mempress-run-tests,
             chipyard-constellation-run-tests,
             tracegen-boom-run-tests,
diff --git a/generators/chipyard/src/main/scala/config/MMIOAcceleratorConfigs.scala b/generators/chipyard/src/main/scala/config/MMIOAcceleratorConfigs.scala
index 6a7710d9..16e6b313 100644
--- a/generators/chipyard/src/main/scala/config/MMIOAcceleratorConfigs.scala
+++ b/generators/chipyard/src/main/scala/config/MMIOAcceleratorConfigs.scala
@@ -61,7 +61,6 @@ class LargeNVDLARocketConfig extends Config(
 class ManyMMIOAcceleratorRocketConfig extends Config(
   new chipyard.iobinders.WithDontTouchIOBinders(false) ++   // TODO: hack around dontTouch not working in SFC
   new fftgenerator.WithFFTGenerator(numPoints=8, width=16, decPt=8) ++ // add 8-point mmio fft at the default addr (0x2400) with 16bit fixed-point numbers.
-  new nvidia.blocks.dla.WithNVDLA("small") ++               // add a small NVDLA
   new chipyard.example.WithStreamingPassthrough ++          // use top with tilelink-controlled streaming passthrough
   new chipyard.example.WithStreamingFIR ++                  // use top with tilelink-controlled streaming FIR
   new freechips.rocketchip.subsystem.WithNBigCores(1) ++