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/piecewise/test_multiple_graphs.py
View File

@@ -14,7 +14,7 @@ from vllm.compilation.counter import compilation_counter
from vllm.compilation.decorators import ignore_torch_compile, support_torch_compile
from vllm.config import (
CompilationConfig,
CompilationLevel,
CompilationMode,
CUDAGraphMode,
VllmConfig,
set_current_vllm_config,
@@ -199,10 +199,10 @@ def test_multi_graph_piecewise_compile(use_inductor_graph_partition: bool):
outputs = []
# piecewise compile
# vllmcompile compile
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],
@@ -251,7 +251,7 @@ def test_multi_graph_piecewise_compile(use_inductor_graph_partition: bool):
# no compile or cudagraph
vllm_config = VllmConfig(
compilation_config=CompilationConfig(
level=CompilationLevel.NO_COMPILATION,
mode=CompilationMode.NONE,
)
)
cudagraph_runtime_mode = CUDAGraphMode.NONE
@@ -280,7 +280,7 @@ def test_multi_graph_piecewise_compile(use_inductor_graph_partition: bool):
# piecewise compile without CUDA graph
vllm_config = VllmConfig(
compilation_config=CompilationConfig(
level=CompilationLevel.PIECEWISE,
mode=CompilationMode.VLLM_COMPILE,
use_cudagraph=False,
splitting_ops=["silly::attention"],
use_inductor_graph_partition=use_inductor_graph_partition,