Skip to content

GitLab

Unverified Commit 1d7f95b8 authored by ElizaWszola's avatar ElizaWszola Committed by GitHub
Browse files

[Compiler] Disable Inductor standalone compile by default (#25391) 


Signed-off-by: default avatarElizaWszola <ewszola@redhat.com>
parent cfbee3d0
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 2 deletions
vllm/envs.py
View file @ 1d7f95b8
......@@ -126,6 +126,7 @@ if TYPE_CHECKING:
VLLM_DP_RANK: int = 0
VLLM_DP_RANK_LOCAL: int = -1
VLLM_DP_SIZE: int = 1
VLLM_USE_STANDALONE_COMPILE: bool = False
VLLM_DP_MASTER_IP: str = ""
VLLM_DP_MASTER_PORT: int = 0
VLLM_MOE_DP_CHUNK_SIZE: int = 256
......@@ -437,9 +438,9 @@ environment_variables: dict[str, Callable[[], Any]] = {
# Feature flag to enable/disable Inductor standalone compile.
# In torch <= 2.7 we ignore this flag; in torch >= 2.8 this is
# enabled by default.
# disabled by default.
"VLLM_USE_STANDALONE_COMPILE":
lambda: os.environ.get("VLLM_USE_STANDALONE_COMPILE", "1") == "1",
lambda: os.environ.get("VLLM_USE_STANDALONE_COMPILE", "0") == "1",
# local rank of the process in the distributed setting, used to determine
# the GPU device id
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment