xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-09 08:47:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Platform] import activation_quant_fusion for CUDA only (#23882)

Browse Source 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan 2025-08-29 13:54:16 +08:00 committed by GitHub
parent 5264015d74
commit 6597d7a456
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/compilation/pass_manager.py
View File

@ -8,13 +8,13 @@ from vllm.logger import init_logger
from vllm.platforms import current_platform from vllm.platforms import current_platform
if current_platform.is_cuda_alike(): if current_platform.is_cuda_alike():
from .activation_quant_fusion import ActivationQuantFusionPass
from .fusion import FusionPass from .fusion import FusionPass
from .fusion_attn import AttnFusionPass from .fusion_attn import AttnFusionPass
if current_platform.is_cuda(): if current_platform.is_cuda():
from .collective_fusion import AllReduceFusionPass, AsyncTPPass from .collective_fusion import AllReduceFusionPass, AsyncTPPass
from .activation_quant_fusion import ActivationQuantFusionPass
from .fix_functionalization import FixFunctionalizationPass from .fix_functionalization import FixFunctionalizationPass
from .inductor_pass import CustomGraphPass, InductorPass, get_pass_context from .inductor_pass import CustomGraphPass, InductorPass, get_pass_context
from .noop_elimination import NoOpEliminationPass from .noop_elimination import NoOpEliminationPass