get formatting script from skypilot

requirements-dev.txt

@@ -1,2 +1,12 @@
-mypy
+# formatting
+yapf==0.32.0
+pylint==2.8.2
+
+# type checking
+mypy==0.991
+types-PyYAML
+types-requests
+types-setuptools
+
+# testing
 pytest

vllm/.pylint

@@ -0,0 +1,450 @@
+# This Pylint rcfile contains a best-effort configuration to uphold the
+# best-practices and style described in the Google Python style guide:
+#   https://google.github.io/styleguide/pyguide.html
+#
+# Its canonical open-source location is:
+#   https://google.github.io/styleguide/pylintrc
+
+[MASTER]
+
+# Files or directories to be skipped. They should be base names, not paths.
+ignore=third_party,ray_patches,providers
+
+# Files or directories matching the regex patterns are skipped. The regex
+# matches against base names, not paths.
+ignore-patterns=
+
+# Pickle collected data for later comparisons.
+persistent=no
+
+# List of plugins (as comma separated values of python modules names) to load,
+# usually to register additional checkers.
+load-plugins=
+
+# Use multiple processes to speed up Pylint.
+jobs=4
+
+# Allow loading of arbitrary C extensions. Extensions are imported into the
+# active Python interpreter and may run arbitrary code.
+unsafe-load-any-extension=no
+
+
+[MESSAGES CONTROL]
+
+# Only show warnings with the listed confidence levels. Leave empty to show
+# all. Valid levels: HIGH, INFERENCE, INFERENCE_FAILURE, UNDEFINED
+confidence=
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time (only on the command line, not in the configuration file where
+# it should appear only once). See also the "--disable" option for examples.
+#enable=
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifiers separated by comma (,) or put this
+# option multiple times (only on the command line, not in the configuration
+# file where it should appear only once).You can also use "--disable=all" to
+# disable everything first and then reenable specific checks. For example, if
+# you want to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use"--disable=all --enable=classes
+# --disable=W"
+disable=abstract-method,
+        apply-builtin,
+        arguments-differ,
+        attribute-defined-outside-init,
+        backtick,
+        bad-option-value,
+        basestring-builtin,
+        buffer-builtin,
+        c-extension-no-member,
+        consider-using-enumerate,
+        cmp-builtin,
+        cmp-method,
+        coerce-builtin,
+        coerce-method,
+        delslice-method,
+        div-method,
+        duplicate-code,
+        eq-without-hash,
+        execfile-builtin,
+        file-builtin,
+        filter-builtin-not-iterating,
+        fixme,
+        getslice-method,
+        global-statement,
+        hex-method,
+        idiv-method,
+        implicit-str-concat-in-sequence,
+        import-error,
+        import-self,
+        import-star-module-level,
+        inconsistent-return-statements,
+        input-builtin,
+        intern-builtin,
+        invalid-str-codec,
+        locally-disabled,
+        logging-format-interpolation,  # FIXME(sky): make pass.
+        logging-fstring-interpolation,  # FIXME(sky): make pass.
+        long-builtin,
+        long-suffix,
+        map-builtin-not-iterating,
+        misplaced-comparison-constant,
+        missing-function-docstring,
+        metaclass-assignment,
+        next-method-called,
+        next-method-defined,
+        no-absolute-import,
+        no-else-break,
+        no-else-continue,
+        no-else-raise,
+        no-else-return,
+        no-init,  # added
+        no-member,
+        no-name-in-module,
+        no-self-use,
+        nonzero-method,
+        oct-method,
+        old-division,
+        old-ne-operator,
+        old-octal-literal,
+        old-raise-syntax,
+        parameter-unpacking,
+        print-statement,
+        raising-string,
+        range-builtin-not-iterating,
+        raw_input-builtin,
+        rdiv-method,
+        reduce-builtin,
+        relative-import,
+        reload-builtin,
+        round-builtin,
+        setslice-method,
+        signature-differs,
+        standarderror-builtin,
+        suppressed-message,
+        sys-max-int,
+        too-few-public-methods,
+        too-many-ancestors,
+        too-many-arguments,
+        too-many-boolean-expressions,
+        too-many-branches,
+        too-many-instance-attributes,
+        too-many-locals,
+        too-many-nested-blocks,
+        too-many-public-methods,
+        too-many-return-statements,
+        too-many-statements,
+        trailing-newlines,
+        unichr-builtin,
+        unicode-builtin,
+        unnecessary-pass,
+        unpacking-in-except,
+        useless-else-on-loop,
+        useless-object-inheritance,
+        useless-suppression,
+        using-cmp-argument,
+        wrong-import-order,
+        xrange-builtin,
+        zip-builtin-not-iterating,
+
+
+[REPORTS]
+
+# Set the output format. Available formats are text, parseable, colorized, msvs
+# (visual studio) and html. You can also give a reporter class, eg
+# mypackage.mymodule.MyReporterClass.
+output-format=text
+
+# Put messages in a separate file for each module / package specified on the
+# command line instead of printing them on stdout. Reports (if any) will be
+# written in a file name "pylint_global.[txt|html]". This option is deprecated
+# and it will be removed in Pylint 2.0.
+files-output=no
+
+# Tells whether to display a full report or only the messages
+reports=no
+
+# Python expression which should return a note less than 10 (10 is the highest
+# note). You have access to the variables errors warning, statement which
+# respectively contain the number of errors / warnings messages and the total
+# number of statements analyzed. This is used by the global evaluation report
+# (RP0004).
+evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10)
+
+# Template used to display messages. This is a python new-style format string
+# used to format the message information. See doc for all details
+#msg-template=
+
+
+[BASIC]
+
+# Good variable names which should always be accepted, separated by a comma
+good-names=main,_
+
+# Bad variable names which should always be refused, separated by a comma
+bad-names=
+
+# Colon-delimited sets of names that determine each other's naming style when
+# the name regexes allow several styles.
+name-group=
+
+# Include a hint for the correct naming format with invalid-name
+include-naming-hint=no
+
+# List of decorators that produce properties, such as abc.abstractproperty. Add
+# to this list to register other decorators that produce valid properties.
+property-classes=abc.abstractproperty,cached_property.cached_property,cached_property.threaded_cached_property,cached_property.cached_property_with_ttl,cached_property.threaded_cached_property_with_ttl
+
+# Regular expression matching correct function names
+function-rgx=^(?:(?P<exempt>setUp|tearDown|setUpModule|tearDownModule)|(?P<camel_case>_?[A-Z][a-zA-Z0-9]*)|(?P<snake_case>_?[a-z][a-z0-9_]*))$
+
+# Regular expression matching correct variable names
+variable-rgx=^[a-z][a-z0-9_]*$
+
+# Regular expression matching correct constant names
+const-rgx=^(_?[A-Z][A-Z0-9_]*|__[a-z0-9_]+__|_?[a-z][a-z0-9_]*)$
+
+# Regular expression matching correct attribute names
+attr-rgx=^_{0,2}[a-z][a-z0-9_]*$
+
+# Regular expression matching correct argument names
+argument-rgx=^[a-z][a-z0-9_]*$
+
+# Regular expression matching correct class attribute names
+class-attribute-rgx=^(_?[A-Z][A-Z0-9_]*|__[a-z0-9_]+__|_?[a-z][a-z0-9_]*)$
+
+# Regular expression matching correct inline iteration names
+inlinevar-rgx=^[a-z][a-z0-9_]*$
+
+# Regular expression matching correct class names
+class-rgx=^_?[A-Z][a-zA-Z0-9]*$
+
+# Regular expression matching correct module names
+module-rgx=^(_?[a-z][a-z0-9_]*|__init__)$
+
+# Regular expression matching correct method names
+method-rgx=(?x)^(?:(?P<exempt>_[a-z0-9_]+__|runTest|setUp|tearDown|setUpTestCase|tearDownTestCase|setupSelf|tearDownClass|setUpClass|(test|assert)_*[A-Z0-9][a-zA-Z0-9_]*|next)|(?P<camel_case>_{0,2}[A-Z][a-zA-Z0-9_]*)|(?P<snake_case>_{0,2}[a-z][a-z0-9_]*))$
+
+# Regular expression which should only match function or class names that do
+# not require a docstring.
+no-docstring-rgx=(__.*__|main|test.*|.*test|.*Test)$
+
+# Minimum line length for functions/classes that require docstrings, shorter
+# ones are exempt.
+docstring-min-length=10
+
+
+[TYPECHECK]
+
+# List of decorators that produce context managers, such as
+# contextlib.contextmanager. Add to this list to register other decorators that
+# produce valid context managers.
+contextmanager-decorators=contextlib.contextmanager,contextlib2.contextmanager
+
+# Tells whether missing members accessed in mixin class should be ignored. A
+# mixin class is detected if its name ends with "mixin" (case insensitive).
+ignore-mixin-members=yes
+
+# List of module names for which member attributes should not be checked
+# (useful for modules/projects where namespaces are manipulated during runtime
+# and thus existing member attributes cannot be deduced by static analysis. It
+# supports qualified module names, as well as Unix pattern matching.
+ignored-modules=
+
+# List of class names for which member attributes should not be checked (useful
+# for classes with dynamically set attributes). This supports the use of
+# qualified names.
+ignored-classes=optparse.Values,thread._local,_thread._local
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E1101 when accessed. Python regular
+# expressions are accepted.
+generated-members=
+
+
+[FORMAT]
+
+# Maximum number of characters on a single line.
+max-line-length=80
+
+# TODO(https://github.com/PyCQA/pylint/issues/3352): Direct pylint to exempt
+# lines made too long by directives to pytype.
+
+# Regexp for a line that is allowed to be longer than the limit.
+ignore-long-lines=(?x)(
+  ^\s*(\#\ )?<?https?://\S+>?$|
+  ^\s*(from\s+\S+\s+)?import\s+.+$)
+
+# Allow the body of an if to be on the same line as the test if there is no
+# else.
+single-line-if-stmt=yes
+
+# List of optional constructs for which whitespace checking is disabled. `dict-
+# separator` is used to allow tabulation in dicts, etc.: {1  : 1,\n222: 2}.
+# `trailing-comma` allows a space between comma and closing bracket: (a, ).
+# `empty-line` allows space-only lines.
+no-space-check=
+
+# Maximum number of lines in a module
+max-module-lines=99999
+
+# String used as indentation unit.  The internal Google style guide mandates 2
+# spaces.  Google's externaly-published style guide says 4, consistent with
+# PEP 8.  Here, we use 2 spaces, for conformity with many open-sourced Google
+# projects (like TensorFlow).
+indent-string='    '
+
+# Number of spaces of indent required inside a hanging  or continued line.
+indent-after-paren=4
+
+# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
+expected-line-ending-format=
+
+
+[MISCELLANEOUS]
+
+# List of note tags to take in consideration, separated by a comma.
+notes=TODO
+
+
+[STRING]
+
+# This flag controls whether inconsistent-quotes generates a warning when the
+# character used as a quote delimiter is used inconsistently within a module.
+check-quote-consistency=yes
+
+
+[VARIABLES]
+
+# Tells whether we should check for unused import in __init__ files.
+init-import=no
+
+# A regular expression matching the name of dummy variables (i.e. expectedly
+# not used).
+dummy-variables-rgx=^\*{0,2}(_$|unused_|dummy_)
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid to define new builtins when possible.
+additional-builtins=
+
+# List of strings which can identify a callback function by name. A callback
+# name must start or end with one of those strings.
+callbacks=cb_,_cb
+
+# List of qualified module names which can have objects that can redefine
+# builtins.
+redefining-builtins-modules=six,six.moves,past.builtins,future.builtins,functools
+
+
+[LOGGING]
+
+# Logging modules to check that the string format arguments are in logging
+# function parameter format
+logging-modules=logging,absl.logging,tensorflow.io.logging
+
+
+[SIMILARITIES]
+
+# Minimum lines number of a similarity.
+min-similarity-lines=4
+
+# Ignore comments when computing similarities.
+ignore-comments=yes
+
+# Ignore docstrings when computing similarities.
+ignore-docstrings=yes
+
+# Ignore imports when computing similarities.
+ignore-imports=no
+
+
+[SPELLING]
+
+# Spelling dictionary name. Available dictionaries: none. To make it working
+# install python-enchant package.
+spelling-dict=
+
+# List of comma separated words that should not be checked.
+spelling-ignore-words=
+
+# A path to a file that contains private dictionary; one word per line.
+spelling-private-dict-file=
+
+# Tells whether to store unknown words to indicated private dictionary in
+# --spelling-private-dict-file option instead of raising a message.
+spelling-store-unknown-words=no
+
+
+[IMPORTS]
+
+# Deprecated modules which should not be used, separated by a comma
+deprecated-modules=regsub,
+                   TERMIOS,
+                   Bastion,
+                   rexec,
+                   sets
+
+# Create a graph of every (i.e. internal and external) dependencies in the
+# given file (report RP0402 must not be disabled)
+import-graph=
+
+# Create a graph of external dependencies in the given file (report RP0402 must
+# not be disabled)
+ext-import-graph=
+
+# Create a graph of internal dependencies in the given file (report RP0402 must
+# not be disabled)
+int-import-graph=
+
+# Force import order to recognize a module as part of the standard
+# compatibility libraries.
+known-standard-library=
+
+# Force import order to recognize a module as part of a third party library.
+known-third-party=enchant, absl
+
+# Analyse import fallback blocks. This can be used to support both Python 2 and
+# 3 compatible code, which means that the block might have code that exists
+# only in one or another interpreter, leading to false positives when analysed.
+analyse-fallback-blocks=no
+
+
+[CLASSES]
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,
+                      __new__,
+                      setUp
+
+# List of member names, which should be excluded from the protected access
+# warning.
+exclude-protected=_asdict,
+                  _fields,
+                  _replace,
+                  _source,
+                  _make
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls,
+                            class_
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg=mcs
+
+
+[EXCEPTIONS]
+
+# Exceptions that will emit a warning when being caught. Defaults to
+# "Exception"
+overgeneral-exceptions=StandardError,
+                       Exception,
+                       BaseException
+
+#######
+
+# https://github.com/edaniszewski/pylint-quotes#configuration
+string-quote=single
+triple-quote=double
+docstring-quote=double

vllm/format.sh

@@ -0,0 +1,112 @@
+#!/usr/bin/env bash
+# YAPF formatter, adapted from ray.
+#
+# Usage:
+#    # Do work and commit your work.
+
+#    # Format files that differ from origin/master.
+#    bash format.sh
+
+#    # Commit changed files with message 'Run yapf and pylint'
+#
+#
+# YAPF + Clang formatter (if installed). This script formats all changed files from the last mergebase.
+# You are encouraged to run this locally before pushing changes for review.
+
+# Cause the script to exit if a single command fails
+set -eo pipefail
+
+# this stops git rev-parse from failing if we run this from the .git directory
+builtin cd "$(dirname "${BASH_SOURCE:-$0}")"
+ROOT="$(git rev-parse --show-toplevel)"
+builtin cd "$ROOT" || exit 1
+
+YAPF_VERSION=$(yapf --version | awk '{print $2}')
+PYLINT_VERSION=$(pylint --version | head -n 1 | awk '{print $2}')
+PYLINT_QUOTES_VERSION=$(pip list | grep pylint-quotes | awk '{print $2}')
+MYPY_VERSION=$(mypy --version | awk '{print $2}')
+BLACK_VERSION=$(black --version | head -n 1 | awk '{print $2}')
+
+# # params: tool name, tool version, required version
+tool_version_check() {
+    if [[ $2 != $3 ]]; then
+        echo "Wrong $1 version installed: $3 is required, not $2."
+        exit 1
+    fi
+}
+
+tool_version_check "yapf" $YAPF_VERSION "$(grep yapf requirements-dev.txt | cut -d'=' -f3)"
+tool_version_check "pylint" $PYLINT_VERSION "$(grep "pylint==" requirements-dev.txt | cut -d'=' -f3)"
+tool_version_check "mypy" "$MYPY_VERSION" "$(grep mypy requirements-dev.txt | cut -d'=' -f3)"
+
+YAPF_FLAGS=(
+    '--recursive'
+    '--parallel'
+)
+
+YAPF_EXCLUDES=(
+    '--exclude' 'build/**'
+)
+
+# Format specified files
+format() {
+    yapf --in-place "${YAPF_FLAGS[@]}" "$@"
+}
+
+# Format files that differ from main branch. Ignores dirs that are not slated
+# for autoformat yet.
+format_changed() {
+    # The `if` guard ensures that the list of filenames is not empty, which
+    # could cause yapf to receive 0 positional arguments, making it hang
+    # waiting for STDIN.
+    #
+    # `diff-filter=ACM` and $MERGEBASE is to ensure we only format files that
+    # exist on both branches.
+    MERGEBASE="$(git merge-base origin/master HEAD)"
+
+    if ! git diff --diff-filter=ACM --quiet --exit-code "$MERGEBASE" -- '*.py' '*.pyi' &>/dev/null; then
+        git diff --name-only --diff-filter=ACM "$MERGEBASE" -- '*.py' '*.pyi' | xargs -P 5 \
+             yapf --in-place "${YAPF_EXCLUDES[@]}" "${YAPF_FLAGS[@]}"
+    fi
+
+}
+
+# Format all files
+format_all() {
+    yapf --in-place "${YAPF_FLAGS[@]}" "${YAPF_EXCLUDES[@]}" sky tests examples
+}
+
+## This flag formats individual files. --files *must* be the first command line
+## arg to use this option.
+if [[ "$1" == '--files' ]]; then
+   format "${@:2}"
+   # If `--all` is passed, then any further arguments are ignored and the
+   # entire python directory is formatted.
+elif [[ "$1" == '--all' ]]; then
+   format_all
+else
+   # Format only the files that changed in last commit.
+   format_changed
+fi
+echo 'vLLM yapf: Done'
+echo 'vLLM Black:'
+black "${BLACK_INCLUDES[@]}"
+
+# Run mypy
+# TODO(zhwu): When more of the codebase is typed properly, the mypy flags
+# should be set to do a more stringent check.
+echo 'vLLM mypy:'
+mypy
+
+# Run Pylint
+echo 'Sky Pylint:'
+pylint vllm
+
+if ! git diff --quiet &>/dev/null; then
+    echo 'Reformatted files. Please review and stage the changes.'
+    echo 'Changes not staged for commit:'
+    echo
+    git --no-pager diff --name-only
+
+    exit 1
+fi