Merge pull request #13 from dtrifiro/sync-with-upstream

sync with IBM/main

Author: z103cb

.buildkite/check-wheel-size.py

@@ -0,0 +1,36 @@
+import os
+import zipfile
+
+MAX_SIZE_MB = 100
+
+
+def print_top_10_largest_files(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)} MBs uncompressed.")
+
+
+def check_wheel_size(directory):
+    for root, _, files in os.walk(directory):
+        for f in files:
+            if f.endswith(".whl"):
+                wheel_path = os.path.join(root, f)
+                wheel_size = os.path.getsize(wheel_path)
+                wheel_size_mb = wheel_size / (1024 * 1024)
+                if wheel_size_mb > MAX_SIZE_MB:
+                    print(
+                        f"Wheel {wheel_path} is too large ({wheel_size_mb} MB) "
+                        f"compare to the allowed size ({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} MB).")
+    return 0
+
+
+if __name__ == "__main__":
+    import sys
+    sys.exit(check_wheel_size(sys.argv[1]))

.buildkite/run-amd-test.sh

@@ -1,38 +1,44 @@
-# This script build the ROCm docker image and run the API server inside the container.
-# It serves a sanity check for compilation and basic model usage.
+# This script build the ROCm docker image and runs test inside it.
 set -ex
 
 # Print ROCm version
+echo "--- ROCm info"
 rocminfo
 
-# Try building the docker image
-docker build -t rocm -f Dockerfile.rocm .
+echo "--- Resetting GPUs"
 
-# Setup cleanup
-remove_docker_container() { docker rm -f rocm || true; }
-trap remove_docker_container EXIT
-remove_docker_container
-
-# Run the image
-docker run --device /dev/kfd --device /dev/dri --network host --name rocm rocm python3 -m vllm.entrypoints.api_server &
-
-# Wait for the server to start
-wait_for_server_to_start() {
-    timeout=300
-    counter=0
-
-    while [ "$(curl -s -o /dev/null -w ''%{http_code}'' localhost:8000/health)" != "200" ]; do
-        sleep 1
-        counter=$((counter + 1))
-        if [ $counter -ge $timeout ]; then
-            echo "Timeout after $timeout seconds"
-            break
+echo "reset" > /opt/amdgpu/etc/gpu_state
+
+while true; do
+        sleep 3
+        if grep -q clean /opt/amdgpu/etc/gpu_state; then
+                echo "GPUs state is \"clean\""
+                break
         fi
-    done
+done
+
+echo "--- Building container"
+sha=$(git rev-parse --short HEAD)
+container_name=rocm_${sha}
+docker build \
+        -t ${container_name} \
+        -f Dockerfile.rocm \
+        --progress plain \
+        .
+
+remove_docker_container() {
+   docker rm -f ${container_name} || docker image rm -f ${container_name} || true
 }
-wait_for_server_to_start
+trap remove_docker_container EXIT
+
+echo "--- Running container"
+
+docker run \
+        --device /dev/kfd --device /dev/dri \
+        --network host \
+        --rm \
+        -e HF_TOKEN \
+        --name ${container_name} \
+        ${container_name} \
+        /bin/bash -c $(echo $1 | sed "s/^'//" | sed "s/'$//")
 
-# Test a simple prompt
-curl -X POST -H "Content-Type: application/json" \
-    localhost:8000/generate \
-    -d '{"prompt": "San Francisco is a"}'

.buildkite/run-benchmarks.sh

@@ -53,6 +53,11 @@ echo '```' >> benchmark_results.md
 tail -n 20 benchmark_serving.txt >> benchmark_results.md # last 20 lines
 echo '```' >> benchmark_results.md
 
+# if the agent binary is not found, skip uploading the results, exit 0
+if [ ! -f /workspace/buildkite-agent ]; then
+    exit 0
+fi
+
 # upload the results to buildkite
 /workspace/buildkite-agent annotate --style "info" --context "benchmark-results" < benchmark_results.md
 

.buildkite/run-neuron-test.sh

@@ -0,0 +1,51 @@
+# This script build the Neuron docker image and run the API server inside the container.
+# It serves a sanity check for compilation and basic model usage.
+set -e
+
+# Try building the docker image
+aws ecr get-login-password --region us-west-2 | docker login --username AWS --password-stdin 763104351884.dkr.ecr.us-west-2.amazonaws.com
+
+# prune old image and containers to save disk space, and only once a day
+# by using a timestamp file in tmp.
+if [ -f /tmp/neuron-docker-build-timestamp ]; then
+    last_build=$(cat /tmp/neuron-docker-build-timestamp)
+    current_time=$(date +%s)
+    if [ $((current_time - last_build)) -gt 86400 ]; then
+        docker system prune -f
+        echo $current_time > /tmp/neuron-docker-build-timestamp
+    fi
+else
+    echo $(date +%s) > /tmp/neuron-docker-build-timestamp
+fi
+
+docker build -t neuron -f Dockerfile.neuron .
+
+# Setup cleanup
+remove_docker_container() { docker rm -f neuron || true; }
+trap remove_docker_container EXIT
+remove_docker_container
+
+# Run the image
+docker run --device=/dev/neuron0 --device=/dev/neuron1 --network host --name neuron neuron python3 -m vllm.entrypoints.api_server \
+       --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 --max-num-seqs 8 --max-model-len 128 --block-size 128 --device neuron --tensor-parallel-size 2 &
+
+# Wait for the server to start
+wait_for_server_to_start() {
+    timeout=300
+    counter=0
+
+    while [ "$(curl -s -o /dev/null -w ''%{http_code}'' localhost:8000/health)" != "200" ]; do
+        sleep 1
+        counter=$((counter + 1))
+        if [ $counter -ge $timeout ]; then
+            echo "Timeout after $timeout seconds"
+            break
+        fi
+    done
+}
+wait_for_server_to_start
+
+# Test a simple prompt
+curl -X POST -H "Content-Type: application/json" \
+    localhost:8000/generate \
+    -d '{"prompt": "San Francisco is a"}'

.buildkite/test-pipeline.yaml

@@ -15,32 +15,41 @@ steps:
   commands:
   - VLLM_ATTENTION_BACKEND=XFORMERS pytest -v -s basic_correctness/test_basic_correctness.py
   - VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s basic_correctness/test_basic_correctness.py
-  - VLLM_ATTENTION_BACKEND=ROCM_FLASH pytest -v -s basic_correctness/test_basic_correctness.py
   - VLLM_ATTENTION_BACKEND=XFORMERS pytest -v -s basic_correctness/test_chunked_prefill.py
   - VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s basic_correctness/test_chunked_prefill.py
-  - VLLM_ATTENTION_BACKEND=ROCM_FLASH pytest -v -s basic_correctness/test_chunked_prefill.py
+  - VLLM_TEST_ENABLE_ARTIFICIAL_PREEMPT=1 pytest -v -s basic_correctness/test_preemption.py
 
 - label: Core Test
+  mirror_hardwares: [amd]
   command: pytest -v -s core
 
 - label: Distributed Comm Ops Test
   command: pytest -v -s test_comm_ops.py
   working_dir: "/vllm-workspace/tests/distributed"
-  num_gpus: 2 # only support 1 or 2 for now.
+  num_gpus: 2
 
 - label: Distributed Tests
   working_dir: "/vllm-workspace/tests/distributed"
+
   num_gpus: 2 # only support 1 or 2 for now.
+  mirror_hardwares: [amd]
+
   commands:
-  - pytest -v -s test_pynccl.py
   - pytest -v -s test_pynccl_library.py
   - TEST_DIST_MODEL=facebook/opt-125m pytest -v -s test_basic_distributed_correctness.py
   - TEST_DIST_MODEL=meta-llama/Llama-2-7b-hf pytest -v -s test_basic_distributed_correctness.py
   - TEST_DIST_MODEL=facebook/opt-125m pytest -v -s test_chunked_prefill_distributed.py
   - TEST_DIST_MODEL=meta-llama/Llama-2-7b-hf pytest -v -s test_chunked_prefill_distributed.py
 
+- label: Distributed Tests (Multiple Groups)
+  working_dir: "/vllm-workspace/tests/distributed"
+  num_gpus: 4
+  commands:
+  - pytest -v -s test_pynccl.py
+
 - label: Engine Test
-  command: pytest -v -s engine tokenization test_sequence.py test_config.py
+  mirror_hardwares: [amd]
+  command: pytest -v -s engine tokenization test_sequence.py test_config.py test_logger.py
 
 - label: Entrypoints Test
   commands:
@@ -50,6 +59,7 @@ steps:
 
 - label: Examples Test
   working_dir: "/vllm-workspace/examples"
+  mirror_hardwares: [amd]
   commands:
     # install aws cli for llava_example.py
     - pip install awscli
@@ -63,29 +73,35 @@ steps:
   parallelism: 4
 
 - label: Models Test
+  mirror_hardwares: [amd]
   commands:
     - bash ../.buildkite/download-images.sh
     - pytest -v -s models --ignore=models/test_llava.py --ignore=models/test_mistral.py
 
 - label: Llava Test
+  mirror_hardwares: [amd]
   commands:
     - bash ../.buildkite/download-images.sh
     - pytest -v -s models/test_llava.py
 
 - label: Prefix Caching Test
+  mirror_hardwares: [amd]
   commands:
     - pytest -v -s prefix_caching
 
 - label: Samplers Test
   command: pytest -v -s samplers
 
 - label: LogitsProcessor Test
+  mirror_hardwares: [amd]
   command: pytest -v -s test_logits_processor.py
 
 - label: Worker Test
+  mirror_hardwares: [amd]
   command: pytest -v -s worker
 
 - label: Speculative decoding tests
+  mirror_hardwares: [amd]
   command: pytest -v -s spec_decode
 
 - label: LoRA Test %N
@@ -98,8 +114,12 @@ steps:
 - label: Metrics Test
   command: pytest -v -s metrics
 
+- label: Quantization Test
+  command: pytest -v -s quantization
+
 - label: Benchmarks
   working_dir: "/vllm-workspace/.buildkite"
+  mirror_hardwares: [amd]
   commands:
   - pip install aiohttp
   - bash run-benchmarks.sh

.buildkite/test-template.j2

@@ -16,12 +16,29 @@ steps:
           limit: 5
   - wait
 
-  - label: "AMD Test"
+  - group: "AMD Tests"
+    depends_on: ~
+    steps:
+    {% for step in steps %}
+    {% if step.mirror_hardwares and "amd" in step.mirror_hardwares %}
+      - label: "AMD: {{ step.label }}"
+        agents:
+          queue: amd
+        command: bash .buildkite/run-amd-test.sh "'cd {{ (step.working_dir or default_working_dir) | safe  }} && {{ step.command  or (step.commands | join(' && ')) | safe }}'"
+        env:
+          DOCKER_BUILDKIT: "1"
+    {% endif %}
+    {% endfor %}
+
+  - label: "Neuron Test"
+    depends_on: ~
     agents:
-      queue: amd
-    command: bash .buildkite/run-amd-test.sh
+      queue: neuron
+    command: bash .buildkite/run-neuron-test.sh
+    soft_fail: true
 
-  - label: "CPU Test"
+  - label: "Intel Test"
+    depends_on: ~
     command: bash .buildkite/run-cpu-test.sh
 
   {% for step in steps %}
@@ -39,6 +56,9 @@ steps:
     plugins:
       - kubernetes:
           podSpec:
+            {% if step.num_gpus %}
+            priorityClassName: gpu-priority-cls-{{ step.num_gpus }}
+            {% endif %}
             volumes:
               - name: dshm
                 emptyDir:

.github/ISSUE_TEMPLATE/200-installation.yml

@@ -18,6 +18,7 @@ body:
       # For security purposes, please feel free to check the contents of collect_env.py before running it.
       python collect_env.py
       ```
+      It is suggested to download and execute the latest script, as vllm might frequently update the diagnosis information needed for accurately and quickly responding to issues.
     value: |
       ```text
       The output of `python collect_env.py`

.github/ISSUE_TEMPLATE/300-usage.yml

@@ -18,6 +18,7 @@ body:
       # For security purposes, please feel free to check the contents of collect_env.py before running it.
       python collect_env.py
       ```
+      It is suggested to download and execute the latest script, as vllm might frequently update the diagnosis information needed for accurately and quickly responding to issues.
     value: |
       ```text
       The output of `python collect_env.py`

.github/ISSUE_TEMPLATE/400-bug report.yml

@@ -18,6 +18,7 @@ body:
       # For security purposes, please feel free to check the contents of collect_env.py before running it.
       python collect_env.py
       ```
+      It is suggested to download and execute the latest script, as vllm might frequently update the diagnosis information needed for accurately and quickly responding to issues.
     value: |
       ```text
       The output of `python collect_env.py`
@@ -57,6 +58,8 @@ body:
       If the code is too long (hopefully, it isn't), feel free to put it in a public gist and link it in the issue: https://gist.github.com.
 
       Please also paste or describe the results you observe instead of the expected results. If you observe an error, please paste the error message including the **full** traceback of the exception. It may be relevant to wrap error messages in ```` ```triple quotes blocks``` ````.
+
+      If you experienced crashes or hangs, it would be helpful to run vllm with `export VLLM_TRACE_FUNCTION=1` . All the function calls in vllm will be recorded. Inspect these log files, and tell which function crashes or hangs.
     placeholder: |
       A clear and concise description of what the bug is.
 

.github/ISSUE_TEMPLATE/700-performance discussion.yml

@@ -39,6 +39,7 @@ body:
       # For security purposes, please feel free to check the contents of collect_env.py before running it.
       python collect_env.py
       ```
+      It is suggested to download and execute the latest script, as vllm might frequently update the diagnosis information needed for accurately and quickly responding to issues.
     value: |
       ```text
       The output of `python collect_env.py`