diff --git a/cpp/tensorrt_llm/kernels/communicationKernels/moeAlltoAllKernels.cu b/cpp/tensorrt_llm/kernels/communicationKernels/moeAlltoAllKernels.cu
index a72d8d95ee6..f32ce4c7d06 100644
--- a/cpp/tensorrt_llm/kernels/communicationKernels/moeAlltoAllKernels.cu
+++ b/cpp/tensorrt_llm/kernels/communicationKernels/moeAlltoAllKernels.cu
@@ -493,7 +493,12 @@ __global__ void moeA2ADispatchKernel(int32_t const* token_selected_experts, // [
 #if !DISABLE_SYNC_FOR_PROFILING
             uint32_t expected_value = *ptrs.flag_val;
 
+#if defined(__CUDA_ARCH__) && __CUDA_ARCH__ >= 900
+            // .acquire and .release qualifiers for fence instruction require sm_90 or higher.
             asm volatile("fence.release.sys;");
+#else
+            asm volatile("fence.acq_rel.sys;");
+#endif
 #pragma unroll 1 // No unroll as one iter is typically enough
             for (int target_rank = lane_id; target_rank < ep_size; target_rank += warpSize)
             {
@@ -525,7 +530,6 @@ __global__ void moeA2ADispatchKernel(int32_t const* token_selected_experts, // [
                     flag_set = flag_value == expected_value;
                 } while (!flag_set);
             }
-            // asm volatile("fence.acquire.sys;");
 #endif
         }
     }
@@ -1018,7 +1022,6 @@ __global__ void moeA2ACombineKernel(
 
         if (blockIdx.x == 0)
         {
-            // asm volatile("fence.release.sys;");
 #pragma unroll 1 // No unroll
             for (int peer_rank = lane_id; peer_rank < ep_size; peer_rank += warpSize)
             {
@@ -1050,7 +1053,12 @@ __global__ void moeA2ACombineKernel(
                 flag_set = flag_value == expected_value;
             } while (!flag_set);
         }
+#if defined(__CUDA_ARCH__) && __CUDA_ARCH__ >= 900
+        // .acquire and .release qualifiers for fence instruction require sm_90 or higher.
         asm volatile("fence.acquire.sys;");
+#else
+        asm volatile("fence.acq_rel.sys;");
+#endif
     }
     __syncthreads();
 #endif
diff --git a/docker/Dockerfile.multi b/docker/Dockerfile.multi
index 74e18b2cd2a..a6bf164d1ad 100644
--- a/docker/Dockerfile.multi
+++ b/docker/Dockerfile.multi
@@ -1,8 +1,8 @@
 # Multi-stage Dockerfile
 ARG BASE_IMAGE=nvcr.io/nvidia/pytorch
 ARG TRITON_IMAGE=nvcr.io/nvidia/tritonserver
-ARG BASE_TAG=25.10-py3
-ARG TRITON_BASE_TAG=25.10-py3
+ARG BASE_TAG=25.12-py3
+ARG TRITON_BASE_TAG=25.12-py3
 ARG DEVEL_IMAGE=devel
 
 FROM ${BASE_IMAGE}:${BASE_TAG} AS base
@@ -147,6 +147,7 @@ RUN --mount=type=cache,target=/root/.cache/pip --mount=type=bind,from=wheel,sour
     pip install /tmp/wheel/tensorrt_llm*.whl
 
 COPY README.md ./
+COPY --from=wheel /src/tensorrt_llm/build/tensorrt_llm*.whl ./
 COPY docs docs
 COPY cpp/include include
 
diff --git a/docker/Makefile b/docker/Makefile
index 519dbbda13d..67c0a36015c 100644
--- a/docker/Makefile
+++ b/docker/Makefile
@@ -202,17 +202,16 @@ jenkins-rockylinux8_%: PYTHON_VERSION_TAG_ID = $(if $(findstring 3.12,${PYTHON_V
 jenkins-rockylinux8_%: IMAGE_WITH_TAG = $(shell . ../jenkins/current_image_tags.properties && echo $$LLM_ROCKYLINUX8_${PYTHON_VERSION_TAG_ID}_DOCKER_IMAGE)
 jenkins-rockylinux8_%: STAGE = tritondevel
 jenkins-rockylinux8_%: BASE_IMAGE = nvcr.io/nvidia/cuda
-# [TODO] Update to NVIDIA CUDA 13.0.2 when it's available
-jenkins-rockylinux8_%: BASE_TAG = 13.0.1-devel-rockylinux8
+jenkins-rockylinux8_%: BASE_TAG = 13.1.0-devel-rockylinux8
 
 rockylinux8_%: STAGE = tritondevel
 rockylinux8_%: BASE_IMAGE = nvcr.io/nvidia/cuda
-rockylinux8_%: BASE_TAG = 13.0.1-devel-rockylinux8
+rockylinux8_%: BASE_TAG = 13.1.0-devel-rockylinux8
 
 # For x86_64 and aarch64
 ubuntu22_%: STAGE = tritondevel
 ubuntu22_%: BASE_IMAGE = nvcr.io/nvidia/cuda
-ubuntu22_%: BASE_TAG = 13.0.1-devel-ubuntu22.04
+ubuntu22_%: BASE_TAG = 13.1.0-devel-ubuntu22.04
 
 trtllm_%: STAGE = release
 trtllm_%: PUSH_TO_STAGING := 0
diff --git a/docker/common/install_cuda_toolkit.sh b/docker/common/install_cuda_toolkit.sh
index 0dc5cb305aa..555a3b348b8 100644
--- a/docker/common/install_cuda_toolkit.sh
+++ b/docker/common/install_cuda_toolkit.sh
@@ -5,7 +5,7 @@ set -ex
 # This script is used for reinstalling CUDA on Rocky Linux 8 with the run file.
 # CUDA version is usually aligned with the latest NGC CUDA image tag.
 # Only use when public CUDA image is not ready.
-CUDA_VER="13.0.2_580.95.05"
+CUDA_VER="13.1.0_590.44.01"
 CUDA_VER_SHORT="${CUDA_VER%_*}"
 
 NVCC_VERSION_OUTPUT=$(nvcc --version)
diff --git a/docker/common/install_polygraphy.sh b/docker/common/install_polygraphy.sh
index 315658d7a0d..da9df649546 100644
--- a/docker/common/install_polygraphy.sh
+++ b/docker/common/install_polygraphy.sh
@@ -5,7 +5,7 @@ set -ex
 if [ -n "${GITHUB_MIRROR}" ]; then
   export PIP_INDEX_URL="https://urm.nvidia.com/artifactory/api/pypi/pypi-remote/simple"
 fi
-pip3 install polygraphy==0.49.9
+pip3 install polygraphy==0.49.26
 
 # Clean up pip cache and temporary files
 pip3 cache purge
diff --git a/docker/common/install_pytorch.sh b/docker/common/install_pytorch.sh
index 069b26846c8..0cf13150199 100644
--- a/docker/common/install_pytorch.sh
+++ b/docker/common/install_pytorch.sh
@@ -5,7 +5,7 @@ set -ex
 # Use latest stable version from https://pypi.org/project/torch/#history
 # and closest to the version specified in
 # https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-25-10.html#rel-25-10
-TORCH_VERSION="2.9.0"
+TORCH_VERSION="2.9.1"
 SYSTEM_ID=$(grep -oP '(?<=^ID=).+' /etc/os-release | tr -d '"')
 
 prepare_environment() {
diff --git a/docker/common/install_tensorrt.sh b/docker/common/install_tensorrt.sh
index 3887be6fa26..f6ae0f3872d 100644
--- a/docker/common/install_tensorrt.sh
+++ b/docker/common/install_tensorrt.sh
@@ -2,20 +2,20 @@
 
 set -ex
 
-TRT_VER="10.13.3.9"
+TRT_VER="10.14.1.48"
 # Align with the pre-installed cuDNN / cuBLAS / NCCL versions from
-# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-25-10.html#rel-25-10
-CUDA_VER="13.0" # 13.0.2
+# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-25-12.html#rel-25-12
+CUDA_VER="13.1" # 13.1.0
 # Keep the installation for cuDNN if users want to install PyTorch with source codes.
 # PyTorch 2.x can compile with cuDNN v9.
-CUDNN_VER="9.14.0.64-1"
-NCCL_VER="2.27.7-1+cuda13.0"
-CUBLAS_VER="13.1.0.3-1"
+CUDNN_VER="9.17.0.29-1"
+NCCL_VER="2.28.9-1+cuda13.0"
+CUBLAS_VER="13.2.0.9-1"
 # Align with the pre-installed CUDA / NVCC / NVRTC versions from
 # https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html
-NVRTC_VER="13.0.88-1"
-CUDA_RUNTIME="13.0.96-1"
-CUDA_DRIVER_VERSION="580.95.05-1.el8"
+NVRTC_VER="13.1.80-1"
+CUDA_RUNTIME="13.1.80-1"
+CUDA_DRIVER_VERSION="590.44.01-1.el8"
 
 for i in "$@"; do
     case $i in
@@ -118,7 +118,12 @@ install_rockylinux_requirements() {
 install_tensorrt() {
     PY_VERSION=$(python3 -c 'import sys; print(".".join(map(str, sys.version_info[0:2])))')
     PARSED_PY_VERSION=$(echo "${PY_VERSION//./}")
+
     TRT_CUDA_VERSION=${CUDA_VER}
+    # No cuda-13.1 version for TensorRT yet, use cuda-13.0 instead
+    if [ "$CUDA_VER" = "13.1" ]; then
+        TRT_CUDA_VERSION="13.0"
+    fi
     TRT_VER_SHORT=$(echo $TRT_VER | cut -d. -f1-3)
 
     if [ -z "$RELEASE_URL_TRT" ];then
diff --git a/jenkins/Build.groovy b/jenkins/Build.groovy
index 261c0a6d3a0..843e78f998c 100644
--- a/jenkins/Build.groovy
+++ b/jenkins/Build.groovy
@@ -83,19 +83,19 @@ def BUILD_CONFIGS = [
     (WHEEL_EXTRA_ARGS) : "--extra-cmake-vars WARNING_IS_ERROR=ON --extra-cmake-vars NIXL_ROOT=/opt/nvidia/nvda_nixl --extra-cmake-vars MOONCAKE_ROOT=/usr/local/Mooncake",
     (TARNAME) : "TensorRT-LLM-GH200.tar.gz",
     (WHEEL_ARCHS): "90-real;100-real;103-real;120-real",
-    (BUILD_JOBS_FOR_CONFIG): "4", // TODO: Remove after fix the build OOM issue on SBSA
+    (BUILD_JOBS_FOR_CONFIG): "8", // TODO: Remove after fix the build OOM issue on SBSA
   ],
   (CONFIG_LINUX_AARCH64_PYBIND): [
     (WHEEL_EXTRA_ARGS) : "--binding_type pybind --extra-cmake-vars WARNING_IS_ERROR=ON --extra-cmake-vars NIXL_ROOT=/opt/nvidia/nvda_nixl --extra-cmake-vars MOONCAKE_ROOT=/usr/local/Mooncake",
     (TARNAME) : "pybind-TensorRT-LLM-GH200.tar.gz",
     (WHEEL_ARCHS): "90-real;100-real;103-real;120-real",
-    (BUILD_JOBS_FOR_CONFIG): "4", // TODO: Remove after fix the build OOM issue on SBSA
+    (BUILD_JOBS_FOR_CONFIG): "8", // TODO: Remove after fix the build OOM issue on SBSA
   ],
   (CONFIG_LINUX_AARCH64_LLVM) : [
     (WHEEL_EXTRA_ARGS) : "--extra-cmake-vars WARNING_IS_ERROR=ON -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_CUDA_HOST_COMPILER=clang -DCMAKE_LINKER_TYPE=LLD",
     (TARNAME) : "llvm-TensorRT-LLM-GH200.tar.gz",
     (WHEEL_ARCHS): "90-real;100-real;103-real;120-real",
-    (BUILD_JOBS_FOR_CONFIG): "4", // TODO: Remove after fix the build OOM issue on SBSA
+    (BUILD_JOBS_FOR_CONFIG): "8", // TODO: Remove after fix the build OOM issue on SBSA
   ],
 ]
 
diff --git a/jenkins/L0_MergeRequest.groovy b/jenkins/L0_MergeRequest.groovy
index 3e81b22a099..324d4337a2f 100644
--- a/jenkins/L0_MergeRequest.groovy
+++ b/jenkins/L0_MergeRequest.groovy
@@ -1092,7 +1092,8 @@ def launchStages(pipeline, reuseBuild, testFilter, enableFailFast, globalVars)
                 }
 
                 if (singleGpuTestFailed) {
-                    if (env.JOB_NAME ==~ /.*PostMerge.*/) {
+                    //if (env.JOB_NAME ==~ /.*PostMerge.*/) {
+                    if (testFilter[(IS_POST_MERGE)] || env.JOB_NAME ==~ /.*PostMerge.*/) {
                         echo "In the official post-merge pipeline, x86_64 single-GPU test failed, whereas multi-GPU test is still kept running."
                     } else {
                         stage("[Test-x86_64-Multi-GPU] Blocked") {
@@ -1196,7 +1197,8 @@ def launchStages(pipeline, reuseBuild, testFilter, enableFailFast, globalVars)
                 }
 
                 if (singleGpuTestFailed) {
-                    if (env.JOB_NAME ==~ /.*PostMerge.*/) {
+                    // if (env.JOB_NAME ==~ /.*PostMerge.*/) {
+                    if (testFilter[(IS_POST_MERGE)] || env.JOB_NAME ==~ /.*PostMerge.*/) {
                         echo "In the official post-merge pipeline, SBSA single-GPU test failed, whereas multi-GPU test is still kept running."
                     } else {
                         stage("[Test-SBSA-Multi-GPU] Blocked") {
diff --git a/jenkins/L0_Test.groovy b/jenkins/L0_Test.groovy
index e39e4e012d9..69c354b51f3 100644
--- a/jenkins/L0_Test.groovy
+++ b/jenkins/L0_Test.groovy
@@ -39,7 +39,7 @@ LLM_ROCKYLINUX8_PY310_DOCKER_IMAGE = env.wheelDockerImagePy310
 LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE = env.wheelDockerImagePy312
 
 // DLFW torch image
-DLFW_IMAGE = "urm.nvidia.com/docker/nvidia/pytorch:25.10-py3"
+DLFW_IMAGE = "urm.nvidia.com/docker/nvidia/pytorch:25.12-py3"
 
 //Ubuntu base image
 UBUNTU_22_04_IMAGE = "urm.nvidia.com/docker/ubuntu:22.04"
@@ -83,7 +83,7 @@ BUILD_CORES_REQUEST = "8"
 BUILD_CORES_LIMIT = "8"
 BUILD_MEMORY_REQUEST = "48Gi"
 BUILD_MEMORY_LIMIT = "96Gi"
-BUILD_JOBS = "4"
+BUILD_JOBS = "8"
 
 SLURM_CORES_REQUEST = "1"
 SLURM_CORES_LIMIT = "1"
@@ -316,6 +316,11 @@ def processShardTestList(llmSrc, testDBList, splitId, splits, perfMode=false) {
                     foundRunningLine = true
                     return false  // Don't include the "Running" line itself
                 }
+                // Stop collecting when we hit the warnings/errors summary separator
+                if (foundRunningLine && line.contains('======================')) {
+                    foundRunningLine = false  // Stop collecting
+                    return false
+                }
 
                 def hasDoubleColon = line.contains('::')
                 def shouldInclude = foundRunningLine && hasDoubleColon
@@ -3329,7 +3334,7 @@ def launchTestJobs(pipeline, testFilter)
     // Python version and OS for sanity check
     x86SanityCheckConfigs = [
         "PY312-DLFW": [
-            LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE,
+            DLFW_IMAGE,
             "B200_PCIe",
             X86_64_TRIPLE,
             false,
@@ -3364,7 +3369,7 @@ def launchTestJobs(pipeline, testFilter)
             AARCH64_TRIPLE,
             false,
             "",
-            UBUNTU_24_04_IMAGE,
+            DLFW_IMAGE,
             true, // Extra PyTorch CUDA 13.0 install
         ],
         "PY312-DLFW": [
@@ -3464,7 +3469,7 @@ def launchTestJobs(pipeline, testFilter)
                             def platform = cpu_arch == X86_64_TRIPLE ? "x86_64" : "sbsa"
                             trtllm_utils.llmExecStepWithRetry(pipeline, script: "wget https://developer.download.nvidia.com/compute/cuda/repos/${ubuntu_version}/${platform}/cuda-keyring_1.1-1_all.deb")
                             trtllm_utils.llmExecStepWithRetry(pipeline, script: "dpkg -i cuda-keyring_1.1-1_all.deb")
-                            trtllm_utils.llmExecStepWithRetry(pipeline, script: "apt-get update && apt-get install -y cuda-toolkit-13-0")
+                            trtllm_utils.llmExecStepWithRetry(pipeline, script: "apt-get update && apt-get install -y cuda-toolkit-13-1")
                         }
                         // Extra PyTorch CUDA 13.0 install for all bare-metal environments (Default PyTorch is for CUDA 12.8)
                         if (values[6]) {
@@ -3472,9 +3477,9 @@ def launchTestJobs(pipeline, testFilter)
                             // Use internal mirror instead of https://download.pytorch.org/whl/cu130 for better network stability.
                             // PyTorch CUDA 13.0 package and torchvision package can be installed as expected.
                             if (k8s_arch == "amd64") {
-                                trtllm_utils.llmExecStepWithRetry(pipeline, script: "pip3 install torch==2.9.0+cu130 torchvision==0.24.0+cu130 --extra-index-url https://urm.nvidia.com/artifactory/api/pypi/pytorch-cu128-remote/simple")
+                                trtllm_utils.llmExecStepWithRetry(pipeline, script: "pip3 install torch==2.9.1+cu130 torchvision==0.24.1+cu130 --extra-index-url https://urm.nvidia.com/artifactory/api/pypi/pytorch-cu128-remote/simple")
                             } else {
-                                trtllm_utils.llmExecStepWithRetry(pipeline, script: "pip3 install torch==2.9.0+cu130 torchvision==0.24.0 --extra-index-url https://urm.nvidia.com/artifactory/api/pypi/pytorch-cu128-remote/simple")
+                                trtllm_utils.llmExecStepWithRetry(pipeline, script: "pip3 install torch==2.9.1+cu130 torchvision==0.24.1 --extra-index-url https://urm.nvidia.com/artifactory/api/pypi/pytorch-cu128-remote/simple")
                             }
                         }
 
diff --git a/jenkins/current_image_tags.properties b/jenkins/current_image_tags.properties
index 32643c10d3c..24e44e26fab 100644
--- a/jenkins/current_image_tags.properties
+++ b/jenkins/current_image_tags.properties
@@ -13,7 +13,7 @@
 #     images are adopted from PostMerge pipelines, the abbreviated commit hash is used instead.
 IMAGE_NAME=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm
 
-LLM_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.10-py3-x86_64-ubuntu24.04-trt10.13.3.9-skip-tritondevel-202512241744-10055
-LLM_SBSA_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.10-py3-aarch64-ubuntu24.04-trt10.13.3.9-skip-tritondevel-202512241744-10055
-LLM_ROCKYLINUX8_PY310_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.0.2-devel-rocky8-x86_64-rocky8-py310-trt10.13.3.9-skip-tritondevel-202512241744-10055
-LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.0.2-devel-rocky8-x86_64-rocky8-py312-trt10.13.3.9-skip-tritondevel-202512241744-10055
+LLM_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.12-py3-x86_64-ubuntu24.04-trt10.14.1.48-skip-tritondevel-202601011103-9818
+LLM_SBSA_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.12-py3-aarch64-ubuntu24.04-trt10.14.1.48-skip-tritondevel-202601011103-9818
+LLM_ROCKYLINUX8_PY310_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.1.0-devel-rocky8-x86_64-rocky8-py310-trt10.14.1.48-skip-tritondevel-202601011103-9818
+LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.1.0-devel-rocky8-x86_64-rocky8-py312-trt10.14.1.48-skip-tritondevel-202601011103-9818
diff --git a/requirements.txt b/requirements.txt
index a21b8ca2819..9c0b705829e 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -19,13 +19,14 @@ pandas
 h5py==3.12.1
 StrEnum
 sentencepiece>=0.1.99
-tensorrt~=10.13.3
-# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-25-10.html#rel-25-10 uses 2.9.0a0.
-torch>=2.9.0a0,<=2.9.0
+tensorrt~=10.14.1
+# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-25-12.html#rel-25-12 uses 2.10.0a0.
+torch>=2.9.1,<=2.10.0a0
 torchvision
 nvidia-modelopt[torch]~=0.37.0
-# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-25-10.html#rel-25-10 uses 2.27.7
-nvidia-nccl-cu13==2.27.7
+# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-25-12.html#rel-25-12 uses 2.28.9
+# torch 2.9.1+cu130 depends on nvidia-nccl-cu13==2.27.7; platform_system == "Linux"
+nvidia-nccl-cu13>=2.27.7,<=2.28.9
 nvidia-cuda-nvrtc
 transformers==4.57.1
 prometheus_client
@@ -65,7 +66,7 @@ ninja
 etcd3 @ git+https://github.com/kragniz/python-etcd3.git@e58a899579ba416449c4e225b61f039457c8072a
 blake3
 soundfile
-triton==3.5.0
+triton==3.5.1
 tiktoken
 blobfile
 openai-harmony==0.0.4
diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt
index a48b99d7edc..76d115326fb 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -495,6 +495,56 @@ examples/test_ray.py::test_ray_disaggregated_serving[tp2] SKIP (https://nvbugs/5
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[latency_trtllmgen] SKIP (https://nvbugs/5715568)
 unittest/executor/test_rpc_proxy.py SKIP (https://nvbugs/5605741)
 unittest/executor/test_rpc_worker.py SKIP (https://nvbugs/5605741)
+cpp/test_e2e.py::test_model[-redrafter-86] SKIP (https://nvbugs/5761642)
+unittest/_torch/auto_deploy/unit/singlegpu/models/test_hybrid_patches.py::test_bamba_patches[ibm-ai-platform/Bamba-9B-v2-True-False] SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/models/test_hybrid_patches.py::test_bamba_patches[ibm-ai-platform/Bamba-9B-v2-True] SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/models/test_hybrid_patches.py::test_bamba_patches[nvidia/NVIDIA-Nemotron-Nano-12B-v2-True-False] SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/transformations/library/test_attention_matcher.py::test_match_repeat_kv[RepeatKVModel-8-4] SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/transformations/library/test_attention_matcher.py::test_match_repeat_kv[RepeatKVModel-8-2] SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/transformations/library/test_attention_matcher.py::test_match_repeat_kv[RepeatKVModel2-8-4] SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/transformations/library/test_attention_matcher.py::test_match_repeat_kv[RepeatKVModel2-8-2] SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/transformations/library/test_attention_matcher.py::test_match_repeat_kv[RepeatKVModel3-8-4] SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/transformations/library/test_attention_matcher.py::test_match_repeat_kv[RepeatKVModel3-8-2] SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/transformations/library/test_attention_matcher.py::test_match_repeat_kv[HFRepeatKVModel-8-4] SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/transformations/library/test_attention_matcher.py::test_match_repeat_kv[HFRepeatKVModel-8-2] SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/transformations/library/test_attention_matcher.py::test_counter_example SKIP (https://nvbugs/5761665)
+unittest/_torch/auto_deploy/unit/singlegpu/transformations/library/test_attention_matcher_hf.py::test_match_llama_attention[eager-config1] SKIP (https://nvbugs/5761665)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scale_gemm[7-7168-2112] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scale_gemm[7-2048-7168] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scale_gemm[16-7168-2112] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scale_gemm[16-2048-7168] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scale_gemm[64-7168-2112] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scale_gemm[64-2048-7168] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scale_gemm[128-7168-2112] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scale_gemm[128-2048-7168] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scale_gemm[4096-7168-2112] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scale_gemm[4096-2048-7168] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_moe_gemm[7168-4096-ms0] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_moe_gemm[7168-4096-ms1] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_moe_gemm[7168-4096-ms2] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_moe_gemm[7168-4096-ms3] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_moe_gemm[2048-7168-ms0] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_moe_gemm[2048-7168-ms1] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_moe_gemm[2048-7168-ms2] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_moe_gemm[2048-7168-ms3] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_bmm[7168-4096-1-1024] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_bmm[7168-4096-2-512] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_bmm[7168-4096-4-256] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_bmm[2048-7168-1-1024] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_bmm[2048-7168-2-512] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/deep_gemm_tests.py::test_fp8_block_scaling_bmm[2048-7168-4-256] SKIP (https://nvbugs/5761699)
+unittest/_torch/thop/parallel/test_fp8_block_scale_gemm.py::test_deep_gemm_in_subprocess[env2] SKIP (https://nvbugs/5766853)
+accuracy/test_llm_api_pytorch_multimodal.py::TestGemma3_27BInstruct::test_auto_dtype SKIP (https://nvbugs/5766864)
+unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_dist_backend.py::test_dist_backend_all_gather[torch] SKIP (https://nvbugs/5766986)
+unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_dist_backend.py::test_dist_backend_all_gather[trtllm] SKIP (https://nvbugs/5766986)
+unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding[Linear-torch_dist_all_gather-False-False-2] SKIP (https://nvbugs/5766982)
+unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding[Linear-torch_dist_all_gather-False-True-2] SKIP (https://nvbugs/5766982)
+unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding[Linear-torch_dist_all_gather-True-False-2] SKIP (https://nvbugs/5766982)
+unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding[Linear-torch_dist_all_gather-True-True-2] SKIP (https://nvbugs/5766982)
+unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding_pattern_detection[Linear-torch_dist_all_gather-False-False-8] SKIP (https://nvbugs/5766974)
+unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding_pattern_detection[Linear-torch_dist_all_gather-False-True-8] SKIP (https://nvbugs/5766974)
+unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding_pattern_detection[Linear-torch_dist_all_gather-True-False-8] SKIP (https://nvbugs/5766974)
+unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding_pattern_detection[Linear-torch_dist_all_gather-True-True-8] SKIP (https://nvbugs/5766974)
 triton_server/test_triton.py::test_gpt_gather_logits[gpt-gather-logits] SKIP (https://nvbugs/5766960)
 stress_test/stress_test.py::test_run_stress_test[llama-v3-8b-instruct-hf_tp1-stress_time_300s_timeout_450s-GUARANTEED_NO_EVICT-pytorch-stress-test] SKIP (https://nvbugs/5766952)
 accuracy/test_llm_api_pytorch.py::TestQwen3NextInstruct::test_bf16_4gpu[tp4ep4_cudagraph_overlap] SKIP (https://nvbugs/5722618)