biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[torch.compile] Reorganize vllm/compilation and tests/compile (0/N for vLLM IR) (#33731)

Browse Source 
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: ProExpertProg <luka.govedic@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Luka Govedič
2026-02-06 07:19:49 -05:00
committed by GitHub
parent f79d9dce16
commit ac32e66cf9
47 changed files with 717 additions and 651 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/config/compilation.py
View File

@@ -11,7 +11,7 @@ from typing import TYPE_CHECKING, Any, ClassVar, Literal
from pydantic import Field, TypeAdapter, field_validator
import vllm.envs as envs
from vllm.compilation.inductor_pass import CallableInductorPass, InductorPass
from vllm.compilation.passes.inductor_pass import CallableInductorPass, InductorPass
from vllm.config.utils import (
Range,
config,
@@ -170,7 +170,9 @@ class PassConfig:
@staticmethod
def default_fi_allreduce_fusion_max_size_mb() -> dict[int, float]:
from vllm.compilation.collective_fusion import FI_ALLREDUCE_FUSION_MAX_SIZE_MB
from vllm.compilation.passes.fusion.allreduce_rms_fusion import (
FI_ALLREDUCE_FUSION_MAX_SIZE_MB,
)
from vllm.platforms import current_platform
if not current_platform.is_cuda():