Merge remote-tracking branch 'upstream/main' into dev

Signed-off-by: Yi Pan <[email protected]>

Author: Conless

.buildkite/release-pipeline.yaml

@@ -7,7 +7,7 @@ steps:
     commands:
       # #NOTE: torch_cuda_arch_list is derived from upstream PyTorch build files here:
       # https://github.com/pytorch/pytorch/blob/main/.ci/aarch64_linux/aarch64_ci_build.sh#L7
-      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.8.1 --build-arg torch_cuda_arch_list='8.7 9.0 10.0+PTX' --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.8.1 --build-arg torch_cuda_arch_list='8.7 9.0 10.0+PTX 12.0' --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
       - "mkdir artifacts"
       - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
       - "bash .buildkite/scripts/upload-wheels.sh"
@@ -62,23 +62,45 @@ steps:
     env:
       DOCKER_BUILDKIT: "1"
 
-  - block: "Build release image"
+  - label: "Build release image (x86)"
     depends_on: ~
-    key: block-release-image-build
-
-  - label: "Build release image"
-    depends_on: block-release-image-build
-    id: build-release-image
+    id: build-release-image-x86
     agents:
       queue: cpu_queue_postmerge
     commands:
       - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.8.1 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT --target vllm-openai --progress plain -f docker/Dockerfile ."
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.8.1 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) --target vllm-openai --progress plain -f docker/Dockerfile ."
+      - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)"
+      # re-tag to default image tag and push, just in case arm64 build fails
+      - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"
       - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"
 
+  - label: "Build release image (arm64)"
+    depends_on: ~
+    id: build-release-image-arm64
+    agents:
+      queue: arm64_cpu_queue_postmerge
+    commands:
+      - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.8.1 --build-arg torch_cuda_arch_list='8.7 9.0 10.0+PTX 12.0' --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) --target vllm-openai --progress plain -f docker/Dockerfile ."
+      - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)"
+
+  # Add job to create multi-arch manifest
+  - label: "Create multi-arch manifest"
+    depends_on:
+      - build-release-image-x86
+      - build-release-image-arm64
+    id: create-multi-arch-manifest
+    agents:
+      queue: cpu_queue_postmerge
+    commands:
+      - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
+      - "docker manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64 --amend"
+      - "docker manifest push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"
+
   - label: "Annotate release workflow"
     depends_on:
-      - build-release-image
+      - create-multi-arch-manifest
       - build-wheel-cuda-12-8
       - build-wheel-cuda-12-6
       - build-wheel-cuda-11-8

.buildkite/scripts/hardware_ci/run-amd-test.sh

@@ -164,7 +164,6 @@ if [[ $commands == *" entrypoints/llm "* ]]; then
   --ignore=entrypoints/llm/test_chat.py \
   --ignore=entrypoints/llm/test_accuracy.py \
   --ignore=entrypoints/llm/test_init.py \
-  --ignore=entrypoints/llm/test_generate_multiple_loras.py \
   --ignore=entrypoints/llm/test_prompt_validation.py "}
 fi
 

.buildkite/scripts/hardware_ci/run-cpu-test.sh

@@ -25,8 +25,8 @@ numactl -C "$CORE_RANGE" -N "$NUMA_NODE" docker build --tag cpu-test-"$NUMA_NODE
 numactl -C "$CORE_RANGE" -N "$NUMA_NODE" docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" --tag cpu-test-"$NUMA_NODE"-avx2 --target vllm-test -f docker/Dockerfile.cpu .
 
 # Run the image, setting --shm-size=4g for tensor parallel.
-docker run -itd --cpuset-cpus="$CORE_RANGE" --cpuset-mems="$NUMA_NODE" --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --env VLLM_CPU_CI_ENV=1 -e E2E_OMP_THREADS="$OMP_CORE_RANGE" --shm-size=4g --name cpu-test-"$NUMA_NODE" cpu-test-"$NUMA_NODE"
-docker run -itd --cpuset-cpus="$CORE_RANGE" --cpuset-mems="$NUMA_NODE" --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --env VLLM_CPU_CI_ENV=1 -e E2E_OMP_THREADS="$OMP_CORE_RANGE" --shm-size=4g --name cpu-test-"$NUMA_NODE"-avx2 cpu-test-"$NUMA_NODE"-avx2
+docker run -itd --cpuset-cpus="$CORE_RANGE" --cpuset-mems="$NUMA_NODE" --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=16 --env VLLM_CPU_CI_ENV=1 -e E2E_OMP_THREADS="$OMP_CORE_RANGE" --shm-size=4g --name cpu-test-"$NUMA_NODE" cpu-test-"$NUMA_NODE"
+docker run -itd --cpuset-cpus="$CORE_RANGE" --cpuset-mems="$NUMA_NODE" --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=16 --env VLLM_CPU_CI_ENV=1 -e E2E_OMP_THREADS="$OMP_CORE_RANGE" --shm-size=4g --name cpu-test-"$NUMA_NODE"-avx2 cpu-test-"$NUMA_NODE"-avx2
 
 function cpu_tests() {
   set -e
@@ -49,57 +49,73 @@ function cpu_tests() {
   # Run kernel tests
   docker exec cpu-test-"$NUMA_NODE" bash -c "
     set -e
-    pytest -v -s tests/kernels/test_onednn.py"
+    pytest -x -v -s tests/kernels/test_onednn.py"
 
   # Run basic model test
   docker exec cpu-test-"$NUMA_NODE" bash -c "
     set -e
     # Note: disable until supports V1
-    # pytest -v -s tests/kernels/attention/test_cache.py -m cpu_model
-    # pytest -v -s tests/kernels/attention/test_mla_decode_cpu.py -m cpu_model
+    # pytest -x -v -s tests/kernels/attention/test_cache.py -m cpu_model
+    # pytest -x -v -s tests/kernels/attention/test_mla_decode_cpu.py -m cpu_model
 
     # Note: disable Bart until supports V1
-    pytest -v -s tests/models/language/generation -m cpu_model \
+    pytest -x -v -s tests/models/language/generation -m cpu_model \
                 --ignore=tests/models/language/generation/test_bart.py
-    VLLM_CPU_SGL_KERNEL=1 pytest -v -s tests/models/language/generation -m cpu_model \
+    VLLM_CPU_SGL_KERNEL=1 pytest -x -v -s tests/models/language/generation -m cpu_model \
                 --ignore=tests/models/language/generation/test_bart.py
 
-    pytest -v -s tests/models/language/pooling -m cpu_model
-    pytest -v -s tests/models/multimodal/generation \
+    pytest -x -v -s tests/models/language/pooling -m cpu_model
+    pytest -x -v -s tests/models/multimodal/generation \
                 --ignore=tests/models/multimodal/generation/test_mllama.py \
                 --ignore=tests/models/multimodal/generation/test_pixtral.py \
                 -m cpu_model"
 
   # Run compressed-tensor test
   docker exec cpu-test-"$NUMA_NODE" bash -c "
     set -e
-    pytest -s -v \
+    pytest -x -s -v \
     tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_logprobs[False-10-32-neuralmagic/Llama-3.2-1B-quantized.w8a8]"
 
   # Note: disable it until supports V1
   # Run AWQ test
   # docker exec cpu-test-"$NUMA_NODE" bash -c "
   #   set -e
-  #   VLLM_USE_V1=0 pytest -s -v \
+  #   VLLM_USE_V1=0 pytest -x -s -v \
   #   tests/quantization/test_ipex_quant.py"
 
   # Run multi-lora tests
   docker exec cpu-test-"$NUMA_NODE" bash -c "
     set -e
-    pytest -s -v \
+    pytest -x -s -v \
     tests/lora/test_qwen2vl.py"
 
-  # online serving
+  # online serving: tp+pp
   docker exec cpu-test-"$NUMA_NODE" bash -c '
     set -e
     VLLM_CPU_OMP_THREADS_BIND=$E2E_OMP_THREADS VLLM_CPU_SGL_KERNEL=1 vllm serve meta-llama/Llama-3.2-3B-Instruct -tp=2 -pp=2 &
+    server_pid=$!
     timeout 600 bash -c "until curl localhost:8000/v1/models; do sleep 1; done" || exit 1
     vllm bench serve \
       --backend vllm \
       --dataset-name random \
       --model meta-llama/Llama-3.2-3B-Instruct \
       --num-prompts 20 \
-      --endpoint /v1/completions'
+      --endpoint /v1/completions
+    kill -s SIGTERM $server_pid &'
+
+  # online serving: tp+dp
+  docker exec cpu-test-"$NUMA_NODE" bash -c '
+    set -e
+    VLLM_CPU_OMP_THREADS_BIND=$E2E_OMP_THREADS VLLM_CPU_SGL_KERNEL=1 vllm serve meta-llama/Llama-3.2-3B-Instruct -tp=2 -dp=2 &
+    server_pid=$!
+    timeout 600 bash -c "until curl localhost:8000/v1/models; do sleep 1; done" || exit 1
+    vllm bench serve \
+      --backend vllm \
+      --dataset-name random \
+      --model meta-llama/Llama-3.2-3B-Instruct \
+      --num-prompts 20 \
+      --endpoint /v1/completions
+    kill -s SIGTERM $server_pid &'
 }
 
 # All of CPU tests are expected to be finished less than 40 mins.

.buildkite/scripts/hardware_ci/run-xpu-test.sh

@@ -31,6 +31,7 @@ docker run \
     set -e
     echo $ZE_AFFINITY_MASK
     VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
+    VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 -O3 -O.cudagraph_mode=NONE
     VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend ray
     VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp
     cd tests

.buildkite/test-pipeline.yaml

@@ -109,10 +109,9 @@ steps:
   - tests/entrypoints/offline_mode
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_lazy_outlines.py --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_generate_multiple_loras.py --ignore=entrypoints/llm/test_collective_rpc.py
+  - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_lazy_outlines.py --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_collective_rpc.py
   - pytest -v -s entrypoints/llm/test_lazy_outlines.py # it needs a clean process
   - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
-  - pytest -v -s entrypoints/llm/test_generate_multiple_loras.py # it needs a clean process
   - VLLM_USE_V1=0 pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests
 
 - label: Entrypoints Test (API Server) # 40min
@@ -234,16 +233,33 @@ steps:
   # OOM in the CI unless we run this separately
   - pytest -v -s tokenization
 
-- label: V1 Test
+- label: V1 Test e2e + engine
   mirror_hardwares: [amdexperimental]
   source_file_dependencies:
     - vllm/
     - tests/v1
   commands:
-    # split the test to avoid interference
-    - pytest -v -s v1/core
+    # TODO: accuracy does not match, whether setting
+    # VLLM_USE_FLASHINFER_SAMPLER or not on H100.
+    - pytest -v -s v1/e2e
     - pytest -v -s v1/engine
+
+- label: V1 Test entrypoints
+  mirror_hardwares: [amdexperimental]
+  source_file_dependencies:
+    - vllm/
+    - tests/v1
+  commands:
     - pytest -v -s v1/entrypoints
+
+- label: V1 Test others
+  mirror_hardwares: [amdexperimental]
+  source_file_dependencies:
+    - vllm/
+    - tests/v1
+  commands:
+    # split the test to avoid interference
+    - pytest -v -s v1/core
     - pytest -v -s v1/executor
     - pytest -v -s v1/sample
     - pytest -v -s v1/logits_processors
@@ -256,9 +272,6 @@ steps:
     - pytest -v -s v1/test_utils.py
     - pytest -v -s v1/test_oracle.py
     - pytest -v -s v1/test_metrics_reader.py
-    # TODO: accuracy does not match, whether setting
-    # VLLM_USE_FLASHINFER_SAMPLER or not on H100.
-    - pytest -v -s v1/e2e
     # Integration test for streaming correctness (requires special branch).
     - pip install -U git+https://github.com/robertgshaw2-redhat/lm-evaluation-harness.git@streaming-api
     - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
@@ -312,7 +325,7 @@ steps:
   source_file_dependencies:
   - vllm/lora
   - tests/lora
-  command: pytest -v -s lora --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --ignore=lora/test_chatglm3_tp.py --ignore=lora/test_llama_tp.py
+  command: pytest -v -s lora --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --ignore=lora/test_chatglm3_tp.py --ignore=lora/test_llama_tp.py --ignore=lora/test_llm_with_multi_loras.py
   parallelism: 4
 
 - label: PyTorch Compilation Unit Tests
@@ -449,8 +462,8 @@ steps:
   - tests/quantization
   commands:
   # temporary install here since we need nightly, will move to requirements/test.in
-  # after torchao 0.12 release
-  - pip install --pre torchao --index-url https://download.pytorch.org/whl/nightly/cu126
+  # after torchao 0.12 release, and pin a working version of torchao nightly here
+  - pip install --pre torchao==0.13.0.dev20250814 --index-url https://download.pytorch.org/whl/nightly/cu128
   - VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization
 
 - label: LM Eval Small Models # 53min
@@ -553,8 +566,7 @@ steps:
   - tests/models/multimodal
   commands:
     - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
-    - pytest -v -s models/multimodal/processing --ignore models/multimodal/processing/test_tensor_schema.py
-    - pytest -v -s models/multimodal/processing/test_tensor_schema.py
+    - pytest -v -s models/multimodal/processing
 
 - label: Multi-Modal Models Test (Standard)
   mirror_hardwares: [amdexperimental]
@@ -654,6 +666,7 @@ steps:
     # Quantization
     - pytest -v -s tests/kernels/quantization/test_cutlass_scaled_mm.py -k 'fp8'
     - pytest -v -s tests/kernels/quantization/test_nvfp4_quant.py
+    - pytest -v -s tests/kernels/quantization/test_silu_nvfp4_quant_fusion.py
     - pytest -v -s tests/kernels/quantization/test_nvfp4_scaled_mm.py
     - pytest -v -s tests/kernels/quantization/test_flashinfer_scaled_mm.py
     - pytest -v -s tests/kernels/quantization/test_flashinfer_nvfp4_scaled_mm.py
@@ -663,6 +676,7 @@ steps:
     - pytest -v -s tests/compile/test_fusion_all_reduce.py
     - pytest -v -s tests/compile/test_fusion_attn.py::test_attention_quant_pattern
     - pytest -v -s tests/kernels/moe/test_flashinfer.py
+    - pytest -v -s tests/compile/test_silu_mul_quant_fusion.py
 
 #####  1 GPU test  #####
 #####  multi gpus test  #####
@@ -755,6 +769,11 @@ steps:
   - pytest -v -s plugins_tests/test_platform_plugins.py
   - pip uninstall vllm_add_dummy_platform -y
   # end platform plugin tests
+  # begin io_processor plugins test, all the code in between uses the prithvi_io_processor plugin
+  - pip install -e ./plugins/prithvi_io_processor_plugin
+  - pytest -v -s plugins_tests/test_io_processor_plugins.py
+  - pip uninstall prithvi_io_processor_plugin -y 
+  # end io_processor plugins test
   # other tests continue here:
   - pytest -v -s plugins_tests/test_scheduler_plugins.py
   - pip install -e ./plugins/vllm_add_dummy_model
@@ -791,13 +810,14 @@ steps:
     # requires multi-GPU testing for validation.
     - pytest -v -s -x lora/test_chatglm3_tp.py
     - pytest -v -s -x lora/test_llama_tp.py
-    - pytest -v -s -x lora/test_multi_loras_with_tp.py
+    - pytest -v -s -x lora/test_llm_with_multi_loras.py
 
 
 - label: Weight Loading Multiple GPU Test  # 33min
   mirror_hardwares: [amdexperimental]
   working_dir: "/vllm-workspace/tests"
-  num_gpus: 2
+  num_gpus: 2 
+  optional: true
   source_file_dependencies:
   - vllm/
   - tests/weight_loading

.github/scale-config.yml

@@ -0,0 +1,21 @@
+# scale-config.yml:
+#   Powers what instance types are available for GHA auto-scaled
+#   runners. Runners listed here will be available as self hosted
+#   runners, configuration is directly pulled from the main branch.
+# runner_types:
+#   runner_label:
+#     instance_type: m4.large
+#     os: linux
+#     # min_available defaults to the global cfg in the ALI Terraform
+#     min_available: undefined
+#     # when max_available value is not defined, no max runners is enforced
+#     max_available: undefined
+#     disk_size: 50
+#     is_ephemeral: true
+
+runner_types:
+  linux.2xlarge:
+    disk_size: 150
+    instance_type: c5.2xlarge
+    is_ephemeral: true
+    os: linux

.github/workflows/issue_autolabel.yml

@@ -49,6 +49,10 @@ jobs:
                     term: "VLLM_ROCM_",
                     searchIn: "both"
                   },
+                  {
+                    term: "aiter",
+                    searchIn: "title"
+                  },
                   {
                     term: "rocm",
                     searchIn: "title"

.pre-commit-config.yaml

@@ -21,7 +21,7 @@ repos:
   - id: ruff-format
     files: ^(.buildkite|benchmarks|examples)/.*
 - repo: https://github.com/crate-ci/typos
-  rev: v1.34.0
+  rev: v1.35.5
   hooks:
   - id: typos
 - repo: https://github.com/PyCQA/isort

CMakeLists.txt

@@ -30,7 +30,7 @@ install(CODE "set(CMAKE_INSTALL_LOCAL_ONLY TRUE)" ALL_COMPONENTS)
 # Supported python versions.  These versions will be searched in order, the
 # first match will be selected.  These should be kept in sync with setup.py.
 #
-set(PYTHON_SUPPORTED_VERSIONS "3.9" "3.10" "3.11" "3.12", "3.13")
+set(PYTHON_SUPPORTED_VERSIONS "3.9" "3.10" "3.11" "3.12" "3.13")
 
 # Supported AMD GPU architectures.
 set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx942;gfx950;gfx1030;gfx1100;gfx1101;gfx1200;gfx1201")
@@ -45,8 +45,8 @@ set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx942;gfx950;gfx1030;gfx1100;gfx1
 # requirements.txt files and should be kept consistent.  The ROCm torch
 # versions are derived from docker/Dockerfile.rocm
 #
-set(TORCH_SUPPORTED_VERSION_CUDA "2.7.1")
-set(TORCH_SUPPORTED_VERSION_ROCM "2.7.0")
+set(TORCH_SUPPORTED_VERSION_CUDA "2.8.0")
+set(TORCH_SUPPORTED_VERSION_ROCM "2.8.0")
 
 #
 # Try to find python package with an executable that exactly matches
@@ -541,6 +541,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
   if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND FP4_ARCHS)
     set(SRCS
       "csrc/quantization/fp4/nvfp4_quant_kernels.cu"
+      "csrc/quantization/fp4/activation_nvfp4_quant_fusion_kernels.cu"
       "csrc/quantization/fp4/nvfp4_scaled_mm_sm120_kernels.cu")
     set_gencode_flags_for_srcs(
       SRCS "${SRCS}"
@@ -559,6 +560,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
   if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND FP4_ARCHS)
     set(SRCS
       "csrc/quantization/fp4/nvfp4_quant_kernels.cu"
+      "csrc/quantization/fp4/activation_nvfp4_quant_fusion_kernels.cu"
       "csrc/quantization/fp4/nvfp4_experts_quant.cu"
       "csrc/quantization/fp4/nvfp4_scaled_mm_kernels.cu"
       "csrc/quantization/fp4/nvfp4_blockwise_moe_kernel.cu")