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

[Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change compilation level to compilation mode, deprecation compilation level (#26355)

Browse Source 
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Morrison Turnansky
2025-10-14 22:51:16 -04:00
committed by GitHub
parent e66d787bce
commit 96b9aa5aa0
42 changed files with 270 additions and 248 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/compile/test_fusion.py
View File

@@ -13,7 +13,7 @@ from vllm.compilation.fusion import (
)
from vllm.compilation.noop_elimination import NoOpEliminationPass
from vllm.compilation.post_cleanup import PostCleanupPass
from vllm.config import CompilationConfig, CompilationLevel, PassConfig, VllmConfig
from vllm.config import CompilationConfig, CompilationMode, PassConfig, VllmConfig
from vllm.model_executor.layers.layernorm import RMSNorm
from vllm.model_executor.layers.quantization.utils.quant_utils import (
GroupShape,
@@ -114,7 +114,7 @@ def test_fusion_rmsnorm_quant(
vllm_config = VllmConfig(
compilation_config=CompilationConfig(
level=CompilationLevel.PIECEWISE,
mode=CompilationMode.VLLM_COMPILE,
custom_ops=["+rms_norm", "+quant_fp8"],
pass_config=PassConfig(enable_fusion=True, enable_noop=True),
)