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

10
tests/compile/test_decorator.py
View File

@@ -8,7 +8,7 @@ from vllm.compilation.decorators import ignore_torch_compile, support_torch_comp
from vllm.config import (
CacheConfig,
CompilationConfig,
CompilationLevel,
CompilationMode,
CUDAGraphMode,
VllmConfig,
set_current_vllm_config,
@@ -66,10 +66,10 @@ def run_model(
def test_ignore_torch_compile_decorator():
# piecewise
# vllmcompile
vllm_config = VllmConfig(
compilation_config=CompilationConfig(
level=CompilationLevel.PIECEWISE,
mode=CompilationMode.VLLM_COMPILE,
use_cudagraph=True,
splitting_ops=["silly::attention"],
cudagraph_capture_sizes=[1, 2],
@@ -185,7 +185,7 @@ def test_conditional_compile_enable_if():
kv_sharing_fast_prefill=True,
),
compilation_config=CompilationConfig(
level=CompilationLevel.PIECEWISE,
mode=CompilationMode.VLLM_COMPILE,
use_cudagraph=True,
splitting_ops=["silly::attention"],
cudagraph_capture_sizes=[1, 2],
@@ -218,7 +218,7 @@ def test_conditional_compile_enable_if():
kv_sharing_fast_prefill=False,
),
compilation_config=CompilationConfig(
level=CompilationLevel.PIECEWISE,
mode=CompilationMode.VLLM_COMPILE,
use_cudagraph=True,
splitting_ops=["silly::attention"],
cudagraph_capture_sizes=[1, 2],