vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-13 00:29:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

support npu

Browse source
This commit is contained in:
Dongjw 2025-07-23 09:54:55 +00:00
parent a641aa8063
commit b982815325
22 changed files with 162 additions and 1562 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ktransformers/operators/linear.py
View file

@ -38,7 +38,10 @@ if not torch.xpu.is_available():
)
from ktransformers.operators.base_operator import BaseInjectedModule
from transformers.configuration_utils import PretrainedConfig
from ktransformers.ktransformers_ext.triton.fp8gemm import fp8_gemm, act_quant, weight_dequant
try:
from ktransformers.ktransformers_ext.triton.fp8gemm import fp8_gemm, act_quant, weight_dequant
except:
print("no triton")
from abc import ABC, abstractmethod
import sys, os
sys.path.append(os.path.join(os.path.dirname(__file__), "..", "ktransformers_ext", "build"))