环境变量#
vLLM 使用以下环境变量来配置系统：
警告
请注意，VLLM_PORT 和 VLLM_HOST_IP 设置的是 vLLM 的 内部使用 端口和 IP。这不是 API 服务器的端口和 IP。如果你使用 --host $VLLM_HOST_IP 和 --port $VLLM_PORT 来启动 API 服务器，它将无法工作。
vLLM 使用的所有环境变量都以 VLLM_ 为前缀。Kubernetes 用户需要特别注意：请不要将服务命名为 vllm，否则 Kubernetes 设置的环境变量可能与 vLLM 的环境变量冲突，因为 Kubernetes 会为每个服务设置以大写服务名称为前缀的环境变量。
environment_variables: Dict[str, Callable[[], Any]] = {
# ================== Installation Time Env Vars ==================
# Target device of vLLM, supporting [cuda (by default),
# rocm, neuron, cpu, openvino]
"VLLM_TARGET_DEVICE":
lambda: os.getenv("VLLM_TARGET_DEVICE", "cuda"),
# Maximum number of compilation jobs to run in parallel.
# By default this is the number of CPUs
"MAX_JOBS":
lambda: os.getenv("MAX_JOBS", None),
# Number of threads to use for nvcc
# By default this is 1.
# If set, `MAX_JOBS` will be reduced to avoid oversubscribing the CPU.
"NVCC_THREADS":
lambda: os.getenv("NVCC_THREADS", None),
# If set, vllm will use precompiled binaries (*.so)
"VLLM_USE_PRECOMPILED":
lambda: bool(os.environ.get("VLLM_USE_PRECOMPILED")),
# CMake build type
# If not set, defaults to "Debug" or "RelWithDebInfo"
# Available options: "Debug", "Release", "RelWithDebInfo"
"CMAKE_BUILD_TYPE":
lambda: os.getenv("CMAKE_BUILD_TYPE"),
# If set, vllm will print verbose logs during installation
"VERBOSE":
lambda: bool(int(os.getenv('VERBOSE', '0'))),
# Root directory for VLLM configuration files
# Defaults to `~/.config/vllm` unless `XDG_CONFIG_HOME` is set
# Note that this not only affects how vllm finds its configuration files
# during runtime, but also affects how vllm installs its configuration
# files during **installation**.
"VLLM_CONFIG_ROOT":
lambda: os.path.expanduser(
os.getenv(
"VLLM_CONFIG_ROOT",
os.path.join(get_default_config_root(), "vllm"),
)),
# ================== Runtime Env Vars ==================
# Root directory for VLLM cache files
# Defaults to `~/.cache/vllm` unless `XDG_CACHE_HOME` is set
"VLLM_CACHE_ROOT":
lambda: os.path.expanduser(
os.getenv(
"VLLM_CACHE_ROOT",
os.path.join(get_default_cache_root(), "vllm"),
)),
# used in distributed environment to determine the ip address
# of the current node, when the node has multiple network interfaces.
# If you are using multi-node inference, you should set this differently
# on each node.
'VLLM_HOST_IP':
lambda: os.getenv('VLLM_HOST_IP', "") or os.getenv("HOST_IP", ""),
# used in distributed environment to manually set the communication port
# Note: if VLLM_PORT is set, and some code asks for multiple ports, the
# VLLM_PORT will be used as the first port, and the rest will be generated
# by incrementing the VLLM_PORT value.
# '0' is used to make mypy happy
'VLLM_PORT':
lambda: int(os.getenv('VLLM_PORT', '0'))
if 'VLLM_PORT' in os.environ else None,
# path used for ipc when the frontend api server is running in
# multi-processing mode to communicate with the backend engine process.
'VLLM_RPC_BASE_PATH':
lambda: os.getenv('VLLM_RPC_BASE_PATH', tempfile.gettempdir()),
# If true, will load models from ModelScope instead of Hugging Face Hub.
# note that the value is true or false, not numbers
"VLLM_USE_MODELSCOPE":
lambda: os.environ.get("VLLM_USE_MODELSCOPE", "False").lower() == "true",
# Instance id represents an instance of the VLLM. All processes in the same
# instance should have the same instance id.
"VLLM_INSTANCE_ID":
lambda: os.environ.get("VLLM_INSTANCE_ID", None),
# Interval in seconds to log a warning message when the ring buffer is full
"VLLM_RINGBUFFER_WARNING_INTERVAL":
lambda: int(os.environ.get("VLLM_RINGBUFFER_WARNING_INTERVAL", "60")),
# path to cudatoolkit home directory, under which should be bin, include,
# and lib directories.
"CUDA_HOME":
lambda: os.environ.get("CUDA_HOME", None),
# Path to the NCCL library file. It is needed because nccl>=2.19 brought
# by PyTorch contains a bug: https://github.com/NVIDIA/nccl/issues/1234
"VLLM_NCCL_SO_PATH":
lambda: os.environ.get("VLLM_NCCL_SO_PATH", None),
# when `VLLM_NCCL_SO_PATH` is not set, vllm will try to find the nccl
# library file in the locations specified by `LD_LIBRARY_PATH`
"LD_LIBRARY_PATH":
lambda: os.environ.get("LD_LIBRARY_PATH", None),
# flag to control if vllm should use triton flash attention
"VLLM_USE_TRITON_FLASH_ATTN":
lambda: (os.environ.get("VLLM_USE_TRITON_FLASH_ATTN", "True").lower() in
("true", "1")),
# Internal flag to enable Dynamo fullgraph capture
"VLLM_TEST_DYNAMO_FULLGRAPH_CAPTURE":
lambda: bool(
os.environ.get("VLLM_TEST_DYNAMO_FULLGRAPH_CAPTURE", "1") != "0"),
"VLLM_TORCH_COMPILE_LEVEL":
lambda: int(os.environ.get("VLLM_TORCH_COMPILE_LEVEL", "0")),
# local rank of the process in the distributed setting, used to determine
# the GPU device id
"LOCAL_RANK":
lambda: int(os.environ.get("LOCAL_RANK", "0")),
# used to control the visible devices in the distributed setting
"CUDA_VISIBLE_DEVICES":
lambda: os.environ.get("CUDA_VISIBLE_DEVICES", None),
# timeout for each iteration in the engine
"VLLM_ENGINE_ITERATION_TIMEOUT_S":
lambda: int(os.environ.get("VLLM_ENGINE_ITERATION_TIMEOUT_S", "60")),
# API key for VLLM API server
"VLLM_API_KEY":
lambda: os.environ.get("VLLM_API_KEY", None),
# S3 access information, used for tensorizer to load model from S3
"S3_ACCESS_KEY_ID":
lambda: os.environ.get("S3_ACCESS_KEY_ID", None),
"S3_SECRET_ACCESS_KEY":
lambda: os.environ.get("S3_SECRET_ACCESS_KEY", None),
"S3_ENDPOINT_URL":
lambda: os.environ.get("S3_ENDPOINT_URL", None),
# Usage stats collection
"VLLM_USAGE_STATS_SERVER":
lambda: os.environ.get("VLLM_USAGE_STATS_SERVER", "https://stats.vllm.ai"),
"VLLM_NO_USAGE_STATS":
lambda: os.environ.get("VLLM_NO_USAGE_STATS", "0") == "1",
"VLLM_DO_NOT_TRACK":
lambda: (os.environ.get("VLLM_DO_NOT_TRACK", None) or os.environ.get(
"DO_NOT_TRACK", None) or "0") == "1",
"VLLM_USAGE_SOURCE":
lambda: os.environ.get("VLLM_USAGE_SOURCE", "production"),
# Logging configuration
# If set to 0, vllm will not configure logging
# If set to 1, vllm will configure logging using the default configuration
# or the configuration file specified by VLLM_LOGGING_CONFIG_PATH
"VLLM_CONFIGURE_LOGGING":
lambda: int(os.getenv("VLLM_CONFIGURE_LOGGING", "1")),
"VLLM_LOGGING_CONFIG_PATH":
lambda: os.getenv("VLLM_LOGGING_CONFIG_PATH"),
# this is used for configuring the default logging level
"VLLM_LOGGING_LEVEL":
lambda: os.getenv("VLLM_LOGGING_LEVEL", "INFO"),
# Trace function calls
# If set to 1, vllm will trace function calls
# Useful for debugging
"VLLM_TRACE_FUNCTION":
lambda: int(os.getenv("VLLM_TRACE_FUNCTION", "0")),
# Backend for attention computation
# Available options:
# - "TORCH_SDPA": use torch.nn.MultiheadAttention
# - "FLASH_ATTN": use FlashAttention
# - "XFORMERS": use XFormers
# - "ROCM_FLASH": use ROCmFlashAttention
# - "FLASHINFER": use flashinfer
"VLLM_ATTENTION_BACKEND":
lambda: os.getenv("VLLM_ATTENTION_BACKEND", None),
# If set, vllm will use flashinfer sampler
"VLLM_USE_FLASHINFER_SAMPLER":
lambda: bool(int(os.getenv("VLLM_USE_FLASHINFER_SAMPLER", "0"))),
# Pipeline stage partition strategy
"VLLM_PP_LAYER_PARTITION":
lambda: os.getenv("VLLM_PP_LAYER_PARTITION", None),
# (CPU backend only) CPU key-value cache space.
# default is 4GB
"VLLM_CPU_KVCACHE_SPACE":
lambda: int(os.getenv("VLLM_CPU_KVCACHE_SPACE", "0")),
# (CPU backend only) CPU core ids bound by OpenMP threads, e.g., "0-31",
# "0,1,2", "0-31,33". CPU cores of different ranks are separated by '|'.
"VLLM_CPU_OMP_THREADS_BIND":
lambda: os.getenv("VLLM_CPU_OMP_THREADS_BIND", "all"),
# OpenVINO device selection
# default is CPU
"VLLM_OPENVINO_DEVICE":
lambda: os.getenv("VLLM_OPENVINO_DEVICE", "CPU").upper(),
# OpenVINO key-value cache space
# default is 4GB
"VLLM_OPENVINO_KVCACHE_SPACE":
lambda: int(os.getenv("VLLM_OPENVINO_KVCACHE_SPACE", "0")),
# OpenVINO KV cache precision
# default is bf16 if natively supported by platform, otherwise f16
# To enable KV cache compression, please, explicitly specify u8
"VLLM_OPENVINO_CPU_KV_CACHE_PRECISION":
lambda: os.getenv("VLLM_OPENVINO_CPU_KV_CACHE_PRECISION", None),
# Enables weights compression during model export via HF Optimum
# default is False
"VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS":
lambda: bool(os.getenv("VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS", False)),
# If the env var is set, then all workers will execute as separate
# processes from the engine, and we use the same mechanism to trigger
# execution on all workers.
# Run vLLM with VLLM_USE_RAY_SPMD_WORKER=1 to enable it.
"VLLM_USE_RAY_SPMD_WORKER":
lambda: bool(int(os.getenv("VLLM_USE_RAY_SPMD_WORKER", "0"))),
# If the env var is set, it uses the Ray's compiled DAG API
# which optimizes the control plane overhead.
# Run vLLM with VLLM_USE_RAY_COMPILED_DAG=1 to enable it.
"VLLM_USE_RAY_COMPILED_DAG":
lambda: bool(int(os.getenv("VLLM_USE_RAY_COMPILED_DAG", "0"))),
# If the env var is set, it uses NCCL for communication in
# Ray's compiled DAG. This flag is ignored if
# VLLM_USE_RAY_COMPILED_DAG is not set.
"VLLM_USE_RAY_COMPILED_DAG_NCCL_CHANNEL":
lambda: bool(int(os.getenv("VLLM_USE_RAY_COMPILED_DAG_NCCL_CHANNEL", "1"))
),
# Use dedicated multiprocess context for workers.
# Both spawn and fork work
"VLLM_WORKER_MULTIPROC_METHOD":
lambda: os.getenv("VLLM_WORKER_MULTIPROC_METHOD", "fork"),
# Path to the cache for storing downloaded assets
"VLLM_ASSETS_CACHE":
lambda: os.path.expanduser(
os.getenv(
"VLLM_ASSETS_CACHE",
os.path.join(get_default_cache_root(), "vllm", "assets"),
)),
# Timeout for fetching images when serving multimodal models
# Default is 5 seconds
"VLLM_IMAGE_FETCH_TIMEOUT":
lambda: int(os.getenv("VLLM_IMAGE_FETCH_TIMEOUT", "5")),
# Timeout for fetching audio when serving multimodal models
# Default is 5 seconds
"VLLM_AUDIO_FETCH_TIMEOUT":
lambda: int(os.getenv("VLLM_AUDIO_FETCH_TIMEOUT", "5")),
# Path to the XLA persistent cache directory.
# Only used for XLA devices such as TPUs.
"VLLM_XLA_CACHE_PATH":
lambda: os.path.expanduser(
os.getenv(
"VLLM_XLA_CACHE_PATH",
os.path.join(get_default_cache_root(), "vllm", "xla_cache"),
)),
"VLLM_FUSED_MOE_CHUNK_SIZE":
lambda: int(os.getenv("VLLM_FUSED_MOE_CHUNK_SIZE", "32768")),
# If set, vllm will skip the deprecation warnings.
"VLLM_NO_DEPRECATION_WARNING":
lambda: bool(int(os.getenv("VLLM_NO_DEPRECATION_WARNING", "0"))),
# If set, the OpenAI API server will stay alive even after the underlying
# AsyncLLMEngine errors and stops serving requests
"VLLM_KEEP_ALIVE_ON_ENGINE_DEATH":
lambda: bool(os.getenv("VLLM_KEEP_ALIVE_ON_ENGINE_DEATH", 0)),
# If the env var VLLM_ALLOW_LONG_MAX_MODEL_LEN is set, it allows
# the user to specify a max sequence length greater than
# the max length derived from the model's config.json.
# To enable this, set VLLM_ALLOW_LONG_MAX_MODEL_LEN=1.
"VLLM_ALLOW_LONG_MAX_MODEL_LEN":
lambda:
(os.environ.get("VLLM_ALLOW_LONG_MAX_MODEL_LEN", "0").strip().lower() in
("1", "true")),
# If set, forces FP8 Marlin to be used for FP8 quantization regardless
# of the hardware support for FP8 compute.
"VLLM_TEST_FORCE_FP8_MARLIN":
lambda:
(os.environ.get("VLLM_TEST_FORCE_FP8_MARLIN", "0").strip().lower() in
("1", "true")),
"VLLM_TEST_FORCE_LOAD_FORMAT":
lambda: os.getenv("VLLM_TEST_FORCE_LOAD_FORMAT", "dummy"),
# Time in ms for the zmq client to wait for a response from the backend
# server for simple data operations
"VLLM_RPC_TIMEOUT":
lambda: int(os.getenv("VLLM_RPC_TIMEOUT", "10000")),
# a list of plugin names to load, separated by commas.
# if this is not set, it means all plugins will be loaded
# if this is set to an empty string, no plugins will be loaded
"VLLM_PLUGINS":
lambda: None if "VLLM_PLUGINS" not in os.environ else os.environ[
"VLLM_PLUGINS"].split(","),
# Enables torch profiler if set. Path to the directory where torch profiler
# traces are saved. Note that it must be an absolute path.
"VLLM_TORCH_PROFILER_DIR":
lambda: (None if os.getenv("VLLM_TORCH_PROFILER_DIR", None) is None else os
.path.expanduser(os.getenv("VLLM_TORCH_PROFILER_DIR", "."))),
# If set, vLLM will use Triton implementations of AWQ.
"VLLM_USE_TRITON_AWQ":
lambda: bool(int(os.getenv("VLLM_USE_TRITON_AWQ", "0"))),
# If set, allow loading or unloading lora adapters in runtime,
"VLLM_ALLOW_RUNTIME_LORA_UPDATING":
lambda:
(os.environ.get("VLLM_ALLOW_RUNTIME_LORA_UPDATING", "0").strip().lower() in
("1", "true")),
# By default, vLLM will check the peer-to-peer capability itself,
# in case of broken drivers. See https://github.com/vllm-project/vllm/blob/a9b15c606fea67a072416ea0ea115261a2756058/vllm/distributed/device_communicators/custom_all_reduce_utils.py#L101-L108 for details. # noqa
# If this env var is set to 1, vLLM will skip the peer-to-peer check,
# and trust the driver's peer-to-peer capability report.
"VLLM_SKIP_P2P_CHECK":
lambda: os.getenv("VLLM_SKIP_P2P_CHECK", "0") == "1",
# If set, allowing the use of deprecated block manager V1
"VLLM_ALLOW_DEPRECATED_BLOCK_MANAGER_V1":
lambda: os.environ.get("VLLM_ALLOW_DEPRECATED_BLOCK_MANAGER_V1", "0"
) == "1",
}