fix: keep partial content when reasoning block is truncated by max_tokens

.buildkite/check-wheel-size.py

@@ -1,53 +1,53 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-import os
-import sys
-import zipfile
-
-# Read the VLLM_MAX_SIZE_MB environment variable, defaulting to 500 MiB
-# Note that we have 800 MiB quota, please use it wisely.
-# See https://github.com/pypi/support/issues/6326 .
-# Please also sync the value with the one in Dockerfile.
-VLLM_MAX_SIZE_MB = int(os.environ.get("VLLM_MAX_SIZE_MB", 500))
-
-
-def print_top_10_largest_files(zip_file):
-    """Print the top 10 largest files in the given zip file."""
-    with zipfile.ZipFile(zip_file, "r") as z:
-        file_sizes = [(f, z.getinfo(f).file_size) for f in z.namelist()]
-        file_sizes.sort(key=lambda x: x[1], reverse=True)
-        for f, size in file_sizes[:10]:
-            print(f"{f}: {size / (1024 * 1024):.2f} MBs uncompressed.")
-
-
-def check_wheel_size(directory):
-    """Check the size of .whl files in the given directory."""
-    for root, _, files in os.walk(directory):
-        for file_name in files:
-            if file_name.endswith(".whl"):
-                wheel_path = os.path.join(root, file_name)
-                wheel_size_mb = os.path.getsize(wheel_path) / (1024 * 1024)
-                if wheel_size_mb > VLLM_MAX_SIZE_MB:
-                    print(
-                        f"Not allowed: Wheel {wheel_path} is larger "
-                        f"({wheel_size_mb:.2f} MB) than the limit "
-                        f"({VLLM_MAX_SIZE_MB} MB)."
-                    )
-                    print_top_10_largest_files(wheel_path)
-                    return 1
-                else:
-                    print(
-                        f"Wheel {wheel_path} is within the allowed size "
-                        f"({wheel_size_mb:.2f} MB)."
-                    )
-    return 0
-
-
-if __name__ == "__main__":
-    if len(sys.argv) < 2:
-        print("Usage: python check-wheel-size.py <directory>")
-        sys.exit(1)
-
-    directory = sys.argv[1]
-    sys.exit(check_wheel_size(directory))
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+import os
+import sys
+import zipfile
+
+# Read the VLLM_MAX_SIZE_MB environment variable, defaulting to 500 MiB
+# Note that we have 800 MiB quota, please use it wisely.
+# See https://github.com/pypi/support/issues/6326 .
+# Please also sync the value with the one in Dockerfile.
+VLLM_MAX_SIZE_MB = int(os.environ.get("VLLM_MAX_SIZE_MB", 500))
+
+
+def print_top_10_largest_files(zip_file):
+    """Print the top 10 largest files in the given zip file."""
+    with zipfile.ZipFile(zip_file, "r") as z:
+        file_sizes = [(f, z.getinfo(f).file_size) for f in z.namelist()]
+        file_sizes.sort(key=lambda x: x[1], reverse=True)
+        for f, size in file_sizes[:10]:
+            print(f"{f}: {size / (1024 * 1024):.2f} MBs uncompressed.")
+
+
+def check_wheel_size(directory):
+    """Check the size of .whl files in the given directory."""
+    for root, _, files in os.walk(directory):
+        for file_name in files:
+            if file_name.endswith(".whl"):
+                wheel_path = os.path.join(root, file_name)
+                wheel_size_mb = os.path.getsize(wheel_path) / (1024 * 1024)
+                if wheel_size_mb > VLLM_MAX_SIZE_MB:
+                    print(
+                        f"Not allowed: Wheel {wheel_path} is larger "
+                        f"({wheel_size_mb:.2f} MB) than the limit "
+                        f"({VLLM_MAX_SIZE_MB} MB)."
+                    )
+                    print_top_10_largest_files(wheel_path)
+                    return 1
+                else:
+                    print(
+                        f"Wheel {wheel_path} is within the allowed size "
+                        f"({wheel_size_mb:.2f} MB)."
+                    )
+    return 0
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: python check-wheel-size.py <directory>")
+        sys.exit(1)
+
+    directory = sys.argv[1]
+    sys.exit(check_wheel_size(directory))

.buildkite/ci_config.yaml

@@ -1,25 +1,25 @@
-name: vllm_ci
-job_dirs:
-  - ".buildkite/image_build"
-  - ".buildkite/test_areas"
-  - ".buildkite/hardware_tests"
-run_all_patterns:
-  - "docker/Dockerfile"
-  - "CMakeLists.txt"
-  - "requirements/common.txt"
-  - "requirements/cuda.txt"
-  - "requirements/build.txt"
-  - "requirements/test.txt"
-  - "setup.py"
-  - "csrc/"
-  - "cmake/"
-run_all_exclude_patterns:
-  - "docker/Dockerfile."
-  - "csrc/cpu/"
-  - "csrc/rocm/"
-  - "cmake/hipify.py"
-  - "cmake/cpu_extension.cmake"
-registries: public.ecr.aws/q9t5s3a7
-repositories:
-  main: "vllm-ci-postmerge-repo"
-  premerge: "vllm-ci-test-repo"
+name: vllm_ci
+job_dirs:
+  - ".buildkite/image_build"
+  - ".buildkite/test_areas"
+  - ".buildkite/hardware_tests"
+run_all_patterns:
+  - "docker/Dockerfile"
+  - "CMakeLists.txt"
+  - "requirements/common.txt"
+  - "requirements/cuda.txt"
+  - "requirements/build.txt"
+  - "requirements/test.txt"
+  - "setup.py"
+  - "csrc/"
+  - "cmake/"
+run_all_exclude_patterns:
+  - "docker/Dockerfile."
+  - "csrc/cpu/"
+  - "csrc/rocm/"
+  - "cmake/hipify.py"
+  - "cmake/cpu_extension.cmake"
+registries: public.ecr.aws/q9t5s3a7
+repositories:
+  main: "vllm-ci-postmerge-repo"
+  premerge: "vllm-ci-test-repo"

.buildkite/hardware_tests/amd.yaml

@@ -1,29 +1,29 @@
-group: Hardware
-steps:
-  - label: "AMD: :docker: build image"
-    depends_on: []
-    device: amd_cpu
-    no_plugin: true
-    commands:
-    - >
-      docker build
-      --build-arg max_jobs=16
-      --build-arg REMOTE_VLLM=1
-      --build-arg ARG_PYTORCH_ROCM_ARCH='gfx90a;gfx942'
-      --build-arg VLLM_BRANCH=$BUILDKITE_COMMIT
-      --tag "rocm/vllm-ci:${BUILDKITE_COMMIT}"
-      -f docker/Dockerfile.rocm
-      --target test
-      --no-cache
-      --progress plain .
-    - docker push "rocm/vllm-ci:${BUILDKITE_COMMIT}"
-    env:
-      DOCKER_BUILDKIT: "1"
-    retry:
-      automatic:
-        - exit_status: -1  # Agent was lost
-          limit: 1
-        - exit_status: -10  # Agent was lost
-          limit: 1
-        - exit_status: 1  # Machine occasionally fail
-          limit: 1
+group: Hardware
+steps:
+  - label: "AMD: :docker: build image"
+    depends_on: []
+    device: amd_cpu
+    no_plugin: true
+    commands:
+    - >
+      docker build
+      --build-arg max_jobs=16
+      --build-arg REMOTE_VLLM=1
+      --build-arg ARG_PYTORCH_ROCM_ARCH='gfx90a;gfx942'
+      --build-arg VLLM_BRANCH=$BUILDKITE_COMMIT
+      --tag "rocm/vllm-ci:${BUILDKITE_COMMIT}"
+      -f docker/Dockerfile.rocm
+      --target test
+      --no-cache
+      --progress plain .
+    - docker push "rocm/vllm-ci:${BUILDKITE_COMMIT}"
+    env:
+      DOCKER_BUILDKIT: "1"
+    retry:
+      automatic:
+        - exit_status: -1  # Agent was lost
+          limit: 1
+        - exit_status: -10  # Agent was lost
+          limit: 1
+        - exit_status: 1  # Machine occasionally fail
+          limit: 1

.buildkite/hardware_tests/arm.yaml

@@ -1,8 +1,8 @@
-group: Hardware
-steps:
-  - label: "Arm CPU Test"
-    soft_fail: true
-    device: arm_cpu
-    no_plugin: true
-    commands: 
-    - bash .buildkite/scripts/hardware_ci/run-cpu-test-arm.sh
+group: Hardware
+steps:
+  - label: "Arm CPU Test"
+    soft_fail: true
+    device: arm_cpu
+    no_plugin: true
+    commands: 
+    - bash .buildkite/scripts/hardware_ci/run-cpu-test-arm.sh

.buildkite/hardware_tests/ascend_npu.yaml

@@ -1,10 +1,10 @@
-group: Hardware
-depends_on: ~
-steps:
-  - label: "Ascend NPU Test"
-    soft_fail: true
-    timeout_in_minutes: 20
-    no_plugin: true
-    device: ascend_npu
-    commands: 
-    - bash .buildkite/scripts/hardware_ci/run-npu-test.sh
+group: Hardware
+depends_on: ~
+steps:
+  - label: "Ascend NPU Test"
+    soft_fail: true
+    timeout_in_minutes: 20
+    no_plugin: true
+    device: ascend_npu
+    commands: 
+    - bash .buildkite/scripts/hardware_ci/run-npu-test.sh

.buildkite/hardware_tests/gh200.yaml

@@ -1,10 +1,10 @@
-group: Hardware
-steps:
-  - label: "GH200 Test"
-    soft_fail: true
-    device: gh200
-    no_plugin: true
-    optional: true
-    commands: 
-    - nvidia-smi 
-    - bash .buildkite/scripts/hardware_ci/run-gh200-test.sh
+group: Hardware
+steps:
+  - label: "GH200 Test"
+    soft_fail: true
+    device: gh200
+    no_plugin: true
+    optional: true
+    commands: 
+    - nvidia-smi 
+    - bash .buildkite/scripts/hardware_ci/run-gh200-test.sh

.buildkite/hardware_tests/intel.yaml

@@ -1,24 +1,24 @@
-group: Hardware
-depends_on: ~
-steps:
-  - label: "Intel CPU Test"
-    soft_fail: true
-    device: intel_cpu
-    no_plugin: true
-    commands: 
-    - bash .buildkite/scripts/hardware_ci/run-cpu-test.sh
-
-  - label: "Intel HPU Test"
-    soft_fail: true
-    device: intel_hpu
-    no_plugin: true
-    commands: 
-    - bash .buildkite/scripts/hardware_ci/run-hpu-test.sh
-
-  - label: "Intel GPU Test"
-    depends_on: []
-    soft_fail: true
-    device: intel_gpu
-    no_plugin: true
-    commands: 
-    - bash .buildkite/scripts/hardware_ci/run-xpu-test.sh
+group: Hardware
+depends_on: ~
+steps:
+  - label: "Intel CPU Test"
+    soft_fail: true
+    device: intel_cpu
+    no_plugin: true
+    commands: 
+    - bash .buildkite/scripts/hardware_ci/run-cpu-test.sh
+  
+  - label: "Intel HPU Test"
+    soft_fail: true
+    device: intel_hpu
+    no_plugin: true
+    commands: 
+    - bash .buildkite/scripts/hardware_ci/run-hpu-test.sh
+
+  - label: "Intel GPU Test"
+    depends_on: []
+    soft_fail: true
+    device: intel_gpu
+    no_plugin: true
+    commands: 
+    - bash .buildkite/scripts/hardware_ci/run-xpu-test.sh