xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-27 17:21:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

revert gtoup shape import

Browse Source 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
This commit is contained in:
vllmellm 2025-12-11 06:48:57 +00:00
parent 52e2a31a95
commit 34e305ec2e
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tests/compile/test_silu_mul_quant_fusion.py
View File

@ -27,6 +27,7 @@ from vllm.config import (
from vllm.model_executor.layers.activation import SiluAndMul from vllm.model_executor.layers.activation import SiluAndMul
from vllm.model_executor.layers.quantization.utils.fp8_utils import W8A8BlockFp8LinearOp from vllm.model_executor.layers.quantization.utils.fp8_utils import W8A8BlockFp8LinearOp
from vllm.model_executor.layers.quantization.utils.quant_utils import ( from vllm.model_executor.layers.quantization.utils.quant_utils import (
GroupShape,
kFp8StaticTensorSym, kFp8StaticTensorSym,
kNvfp4Quant, kNvfp4Quant,
) )