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_fusions_e2e.py
View File

@@ -151,7 +151,7 @@ def test_attn_quant(
cudagraph_mode=mode,
splitting_ops=splitting_ops,
# Common
level=CompilationMode.VLLM_COMPILE,
mode=CompilationMode.VLLM_COMPILE,
pass_config=PassConfig(enable_attn_fusion=True, enable_noop=True),
# Inductor caches custom passes by default as well via uuid
inductor_compile_config={"force_disable_caches": True},
@@ -236,7 +236,7 @@ def test_tp2_attn_quant_allreduce_rmsnorm(
custom_ops=custom_ops_list,
splitting_ops=splitting_ops,
# Common
level=CompilationMode.VLLM_COMPILE,
mode=CompilationMode.VLLM_COMPILE,
pass_config=PassConfig(
enable_attn_fusion=True,
enable_noop=True,
@@ -273,7 +273,7 @@ def run_model(compile_config: int | CompilationConfig, model: str, **model_kwarg
compilation_config = (
compile_config
if isinstance(compile_config, CompilationConfig)
else CompilationConfig(level=compile_config)
else CompilationConfig(mode=compile_config)
)
prompts = [