[vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823)

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Luka Govedič
2026-05-01 23:41:15 -04:00
committed by GitHub
parent 3e49479c4b
commit d58c42e19c
44 changed files with 2833 additions and 779 deletions
+3 -2
View File
@@ -143,7 +143,7 @@ if TYPE_CHECKING:
VLLM_DP_RANK_LOCAL: int = -1
VLLM_DP_SIZE: int = 1
VLLM_USE_STANDALONE_COMPILE: bool = True
VLLM_ENABLE_PREGRAD_PASSES: bool = False
VLLM_ENABLE_PREGRAD_PASSES: bool = True
VLLM_DP_MASTER_IP: str = ""
VLLM_DP_MASTER_PORT: int = 0
VLLM_RANDOMIZE_DP_DUMMY_INPUTS: bool = False
@@ -620,9 +620,10 @@ environment_variables: dict[str, Callable[[], Any]] = {
# The pre-grad passes get run even on cache-hit and negatively impact
# vllm cold compile times by O(1s)
# Can remove this after the following issue gets fixed
# TODO(luka): maybe_inplace requires this
# https://github.com/pytorch/pytorch/issues/174502
"VLLM_ENABLE_PREGRAD_PASSES": lambda: (
os.environ.get("VLLM_ENABLE_PREGRAD_PASSES", "0") == "1"
os.environ.get("VLLM_ENABLE_PREGRAD_PASSES", "1") == "1"
),
# Debug pattern matching inside custom passes.
# Should be set to the fx.Node name (e.g. 'getitem_34' or 'scaled_mm_3').