A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 8, 16:30 UTC
[ROCm][Bugfix] fix act_quant_fusion module import error (#34069)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Feb 7, 2026 at 21:21 UTC
ab10d798555ee3611f82e71cbe573086fb92a4ed
1 file changed
+1
-1
vllm/compilation/passes/fusion/rocm_aiter_fusion.py
+1
-1
@@ -18,9 +18,9 @@ from vllm.model_executor.layers.quantization.utils.quant_utils import (
18
)
19
from vllm.platforms import current_platform
20
21
-from ..activation_quant_fusion import ActivationQuantPattern
21
from ..inductor_pass import enable_fake_mode
22
from ..vllm_inductor_pass import VllmInductorPass, VllmPatternMatcherPass
23
+from .act_quant_fusion import ActivationQuantPattern
24
from .matcher_utils import (
25
MatcherFusedAddRMSNorm,
26
MatcherQuantFP8,