Merge branch 'main' into patches
This commit is contained in:
@@ -247,6 +247,7 @@ if TYPE_CHECKING:
|
||||
VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE: int = 163840
|
||||
VLLM_TOOL_PARSE_REGEX_TIMEOUT_SECONDS: int = 1
|
||||
VLLM_ENFORCE_STRICT_TOOL_CALLING: bool = True
|
||||
VLLM_BEAM_ALWAYS_CONSTRAIN_OUTPUT: bool = True
|
||||
VLLM_MQ_MAX_CHUNK_BYTES_MB: int = 16
|
||||
VLLM_EXECUTE_MODEL_TIMEOUT_SECONDS: int = 300
|
||||
VLLM_WORKER_SHUTDOWN_TIMEOUT_SECONDS: int = 5
|
||||
@@ -1854,6 +1855,11 @@ environment_variables: dict[str, Callable[[], Any]] = {
|
||||
"VLLM_ENFORCE_STRICT_TOOL_CALLING": lambda: (
|
||||
os.getenv("VLLM_ENFORCE_STRICT_TOOL_CALLING", "True").lower() in ("true", "1")
|
||||
),
|
||||
# Constrain every `beam` output to its response template's format, also
|
||||
# without tool or structured output constraints.
|
||||
"VLLM_BEAM_ALWAYS_CONSTRAIN_OUTPUT": lambda: (
|
||||
os.getenv("VLLM_BEAM_ALWAYS_CONSTRAIN_OUTPUT", "True").lower() in ("true", "1")
|
||||
),
|
||||
# Control the max chunk bytes (in MB) for the rpc message queue.
|
||||
# Object larger than this threshold will be broadcast to worker
|
||||
# processes via zmq.
|
||||
@@ -2376,6 +2382,7 @@ def compile_factors() -> dict[str, object]:
|
||||
"VLLM_RANDOMIZE_DP_DUMMY_INPUTS",
|
||||
"VLLM_MODEL_REDIRECT_PATH",
|
||||
"VLLM_HOST_IP",
|
||||
"VLLM_RAY_BUNDLE_INDICES",
|
||||
"VLLM_ELASTIC_EP_SCALE_UP_LAUNCH",
|
||||
"VLLM_FORCE_AOT_LOAD",
|
||||
"S3_ACCESS_KEY_ID",
|
||||
|
||||
Reference in New Issue
Block a user