Skip to content

Commit

Permalink
Merge branch 'upstream_main'
Browse files Browse the repository at this point in the history
  • Loading branch information
flaviabeo committed Nov 6, 2024
2 parents 480287e + 2003cc3 commit f0ccb8c
Show file tree
Hide file tree
Showing 339 changed files with 11,442 additions and 4,091 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@

def read_markdown(file):
if os.path.exists(file):
with open(file, "r") as f:
with open(file) as f:
return f.read() + "\n"
else:
return f"{file} not found.\n"
Expand All @@ -75,14 +75,14 @@ def results_to_json(latency, throughput, serving):
# collect results
for test_file in results_folder.glob("*.json"):

with open(test_file, "r") as f:
with open(test_file) as f:
raw_result = json.loads(f.read())

if "serving" in str(test_file):
# this result is generated via `benchmark_serving.py`

# attach the benchmarking command to raw_result
with open(test_file.with_suffix(".commands"), "r") as f:
with open(test_file.with_suffix(".commands")) as f:
command = json.loads(f.read())
raw_result.update(command)

Expand All @@ -97,7 +97,7 @@ def results_to_json(latency, throughput, serving):
# this result is generated via `benchmark_latency.py`

# attach the benchmarking command to raw_result
with open(test_file.with_suffix(".commands"), "r") as f:
with open(test_file.with_suffix(".commands")) as f:
command = json.loads(f.read())
raw_result.update(command)

Expand All @@ -119,7 +119,7 @@ def results_to_json(latency, throughput, serving):
# this result is generated via `benchmark_throughput.py`

# attach the benchmarking command to raw_result
with open(test_file.with_suffix(".commands"), "r") as f:
with open(test_file.with_suffix(".commands")) as f:
command = json.loads(f.read())
raw_result.update(command)

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -72,15 +72,15 @@ def main(args):

# collect results
for test_file in results_folder.glob("*_nightly_results.json"):
with open(test_file, "r") as f:
with open(test_file) as f:
results = results + json.loads(f.read())

# generate markdown table
df = pd.DataFrame.from_dict(results)

md_table = tabulate(df, headers='keys', tablefmt='pipe', showindex=False)

with open(args.description, "r") as f:
with open(args.description) as f:
description = f.read()

description = description.format(
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -36,11 +36,11 @@
# collect results
for test_file in results_folder.glob("*.json"):

with open(test_file, "r") as f:
with open(test_file) as f:
raw_result = json.loads(f.read())

# attach the benchmarking command to raw_result
with open(test_file.with_suffix(".commands"), "r") as f:
with open(test_file.with_suffix(".commands")) as f:
command = json.loads(f.read())
raw_result.update(command)

Expand Down
11 changes: 6 additions & 5 deletions .buildkite/run-amd-test.sh
Original file line number Diff line number Diff line change
Expand Up @@ -107,11 +107,12 @@ fi
PARALLEL_JOB_COUNT=8
# check if the command contains shard flag, we will run all shards in parallel because the host have 8 GPUs.
if [[ $commands == *"--shard-id="* ]]; then
# assign job count as the number of shards used
commands=${commands//"--num-shards= "/"--num-shards=${PARALLEL_JOB_COUNT} "}
for GPU in $(seq 0 $(($PARALLEL_JOB_COUNT-1))); do
#replace shard arguments
commands=${commands//"--shard-id= "/"--shard-id=${GPU} "}
commands=${commands//"--num-shards= "/"--num-shards=${PARALLEL_JOB_COUNT} "}
echo "Shard ${GPU} commands:$commands"
# assign shard-id for each shard
commands_gpu=${commands//"--shard-id= "/"--shard-id=${GPU} "}
echo "Shard ${GPU} commands:$commands_gpu"
docker run \
--device /dev/kfd --device /dev/dri \
--network host \
Expand All @@ -123,7 +124,7 @@ if [[ $commands == *"--shard-id="* ]]; then
-e HF_HOME=${HF_MOUNT} \
--name ${container_name}_${GPU} \
${image_name} \
/bin/bash -c "${commands}" \
/bin/bash -c "${commands_gpu}" \
|& while read -r line; do echo ">>Shard $GPU: $line"; done &
PIDS+=($!)
done
Expand Down
2 changes: 1 addition & 1 deletion .buildkite/run-openvino-test.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,4 +11,4 @@ trap remove_docker_container EXIT
remove_docker_container

# Run the image and launch offline inference
docker run --network host --env VLLM_OPENVINO_KVCACHE_SPACE=1 --name openvino-test openvino-test python3 /workspace/vllm/examples/offline_inference.py
docker run --network host --env VLLM_OPENVINO_KVCACHE_SPACE=1 --name openvino-test openvino-test python3 /workspace/examples/offline_inference.py
2 changes: 1 addition & 1 deletion .buildkite/run-tpu-test.sh
Original file line number Diff line number Diff line change
Expand Up @@ -12,4 +12,4 @@ remove_docker_container
# For HF_TOKEN.
source /etc/environment
# Run a simple end-to-end example.
docker run --privileged --net host --shm-size=16G -it -e HF_TOKEN=$HF_TOKEN --name tpu-test vllm-tpu /bin/bash -c "python3 -m pip install git+https://github.com/thuml/depyf.git && python3 -m pip install pytest && pytest -v -s /workspace/vllm/tests/tpu/test_custom_dispatcher.py && python3 /workspace/vllm/tests/tpu/test_compilation.py && python3 /workspace/vllm/examples/offline_inference_tpu.py"
docker run --privileged --net host --shm-size=16G -it -e HF_TOKEN=$HF_TOKEN --name tpu-test vllm-tpu /bin/bash -c "python3 -m pip install git+https://github.com/thuml/depyf.git && python3 -m pip install pytest && python3 -m pip install lm_eval[api]==0.4.4 && pytest -v -s /workspace/vllm/tests/entrypoints/openai/test_accuracy.py && pytest -v -s /workspace/vllm/tests/tpu/test_custom_dispatcher.py && python3 /workspace/vllm/tests/tpu/test_compilation.py && python3 /workspace/vllm/examples/offline_inference_tpu.py"
4 changes: 2 additions & 2 deletions .buildkite/test-pipeline.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -321,15 +321,14 @@ steps:
- tests/models/decoder_only/language
commands:
- pytest -v -s models/decoder_only/language/test_models.py
- pytest -v -s models/decoder_only/language/test_big_models.py

- label: Decoder-only Language Models Test (Extended) # 1h20min
nightly: true
source_file_dependencies:
- vllm/
- tests/models/decoder_only/language
commands:
- pytest -v -s models/decoder_only/language --ignore=models/decoder_only/language/test_models.py --ignore=models/decoder_only/language/test_big_models.py
- pytest -v -s models/decoder_only/language --ignore=models/decoder_only/language/test_models.py

- label: Decoder-only Multi-Modal Models Test (Standard)
#mirror_hardwares: [amd]
Expand Down Expand Up @@ -511,6 +510,7 @@ steps:
# NOTE: don't test llama model here, it seems hf implementation is buggy
# see https://github.com/vllm-project/vllm/pull/5689 for details
- pytest -v -s distributed/test_custom_all_reduce.py
- torchrun --nproc_per_node=2 distributed/test_ca_buffer_sharing.py
- TARGET_TEST_SUITE=A100 pytest basic_correctness/ -v -s -m distributed_2_gpus
- pytest -v -s -x lora/test_mixtral.py

Expand Down
25 changes: 25 additions & 0 deletions .github/dependabot.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,3 +5,28 @@ updates:
directory: "/"
schedule:
interval: "weekly"
- package-ecosystem: "pip"
directory: "/"
schedule:
interval: "weekly"
labels: ["dependencies"]
open-pull-requests-limit: 5
reviewers: ["khluu", "simon-mo"]
allow:
- dependency-type: "all"
ignore:
- dependency-name: "torch"
- dependency-name: "torchvision"
- dependency-name: "xformers"
- dependency-name: "lm-format-enforcer"
- dependency-name: "gguf"
- dependency-name: "compressed-tensors"
- dependency-name: "ray[adag]"
- dependency-name: "lm-eval"
groups:
patch-update:
applies-to: version-updates
update-types: ["patch"]
minor-update:
applies-to: version-updates
update-types: ["minor"]
2 changes: 2 additions & 0 deletions .github/workflows/actionlint.yml
Original file line number Diff line number Diff line change
Expand Up @@ -6,12 +6,14 @@ on:
paths:
- '.github/workflows/*.ya?ml'
- '.github/workflows/actionlint.*'
- '.github/workflows/matchers/actionlint.json'
pull_request:
branches:
- "main"
paths:
- '.github/workflows/*.ya?ml'
- '.github/workflows/actionlint.*'
- '.github/workflows/matchers/actionlint.json'

env:
LC_ALL: en_US.UTF-8
Expand Down
12 changes: 12 additions & 0 deletions .github/workflows/clang-format.yml
Original file line number Diff line number Diff line change
Expand Up @@ -6,9 +6,21 @@ on:
push:
branches:
- main
paths:
- '**/*.h'
- '**/*.cpp'
- '**/*.cu'
- '**/*.cuh'
- '.github/workflows/clang-format.yml'
pull_request:
branches:
- main
paths:
- '**/*.h'
- '**/*.cpp'
- '**/*.cu'
- '**/*.cuh'
- '.github/workflows/clang-format.yml'

jobs:
clang-format:
Expand Down
12 changes: 11 additions & 1 deletion .github/workflows/mypy.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -6,16 +6,26 @@ on:
push:
branches:
- main
paths:
- '**/*.py'
- '.github/workflows/mypy.yaml'
- 'tools/mypy.sh'
- 'pyproject.toml'
pull_request:
branches:
- main
paths:
- '**/*.py'
- '.github/workflows/mypy.yaml'
- 'tools/mypy.sh'
- 'pyproject.toml'

jobs:
mypy:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
python-version: ["3.9", "3.10", "3.11", "3.12"]
steps:
- uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
- name: Set up Python ${{ matrix.python-version }}
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/publish.yml
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ jobs:
fail-fast: false
matrix:
os: ['ubuntu-20.04']
python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
python-version: ['3.9', '3.10', '3.11', '3.12']
pytorch-version: ['2.4.0'] # Must be the most recent version that meets requirements-cuda.txt.
cuda-version: ['11.8', '12.1']

Expand Down
49 changes: 29 additions & 20 deletions .github/workflows/ruff.yml
Original file line number Diff line number Diff line change
Expand Up @@ -6,33 +6,42 @@ on:
push:
branches:
- main
paths:
- "**/*.py"
- pyproject.toml
- requirements-lint.txt
- .github/workflows/matchers/ruff.json
- .github/workflows/ruff.yml
pull_request:
branches:
- main
paths:
- "**/*.py"
- pyproject.toml
- requirements-lint.txt
- .github/workflows/matchers/ruff.json
- .github/workflows/ruff.yml

jobs:
ruff:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
python-version: ["3.12"]
steps:
- uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements-lint.txt
- name: Analysing the code with ruff
run: |
echo "::add-matcher::.github/workflows/matchers/ruff.json"
ruff check --output-format github .
- name: Spelling check with codespell
run: |
codespell --toml pyproject.toml
- name: Run isort
run: |
isort . --check-only
- uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements-lint.txt
- name: Analysing the code with ruff
run: |
echo "::add-matcher::.github/workflows/matchers/ruff.json"
ruff check --output-format github .
- name: Run isort
run: |
isort . --check-only
35 changes: 21 additions & 14 deletions .github/workflows/yapf.yml
Original file line number Diff line number Diff line change
Expand Up @@ -6,26 +6,33 @@ on:
push:
branches:
- main
paths:
- "**/*.py"
- .github/workflows/yapf.yml
pull_request:
branches:
- main
paths:
- "**/*.py"
- .github/workflows/yapf.yml

jobs:
yapf:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
python-version: ["3.12"]
steps:
- uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install yapf==0.32.0
pip install toml==0.10.2
- name: Running yapf
run: |
yapf --diff --recursive .
- uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install yapf==0.32.0
pip install toml==0.10.2
- name: Running yapf
run: |
yapf --diff --recursive .
11 changes: 5 additions & 6 deletions .readthedocs.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -6,17 +6,16 @@ version: 2
build:
os: ubuntu-22.04
tools:
python: "3.8"
python: '3.9'

sphinx:
configuration: docs/source/conf.py
fail_on_warning: true
configuration: docs/source/conf.py
fail_on_warning: true

# If using Sphinx, optionally build your docs in additional formats such as PDF
formats: []

# Optionally declare the Python requirements required to build your docs
python:
install:
- requirements: docs/requirements-docs.txt

install:
- requirements: docs/requirements-docs.txt
Loading

0 comments on commit f0ccb8c

Please sign in to comment.