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

Remove last level references not removed in #26355 (#27260)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-22 10:18:17 +01:00
committed by GitHub
parent ed540d6d4c
commit 8f18feb191
6 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/compile/test_config.py
View File

@@ -168,7 +168,7 @@ def test_splitting_ops_dynamic():
if is_torch_equal_or_newer("2.9.0.dev"):
config = VllmConfig(
compilation_config=CompilationConfig(
level=CompilationMode.VLLM_COMPILE,
mode=CompilationMode.VLLM_COMPILE,
use_inductor_graph_partition=True,
splitting_ops=["vllm::unified_attention"],
)
@@ -180,7 +180,7 @@ def test_splitting_ops_dynamic():
# When attn_fusion pass enabled, splitting_ops now default to attention ops.
config = VllmConfig(
compilation_config=CompilationConfig(
level=CompilationMode.VLLM_COMPILE,
mode=CompilationMode.VLLM_COMPILE,
pass_config={"enable_attn_fusion": True, "enable_noop": True},
custom_ops=["+quant_fp8"],
cudagraph_mode=CUDAGraphMode.PIECEWISE,
@@ -195,7 +195,7 @@ def test_splitting_ops_dynamic():
if is_torch_equal_or_newer("2.9.0.dev"):
config = VllmConfig(
compilation_config=CompilationConfig(
level=CompilationMode.VLLM_COMPILE,
mode=CompilationMode.VLLM_COMPILE,
use_inductor_graph_partition=True,
pass_config={"enable_attn_fusion": True, "enable_noop": True},
custom_ops=["+quant_fp8"],