vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-14 17:19:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

support safetensor load, delete architectures argument

Browse source
This commit is contained in:
qiyuxinlin 2025-05-09 10:38:29 +00:00
parent 900a7f7c3e
commit c6aa379de2
30 changed files with 1075 additions and 328 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/tests/dequant_gpu_t.py
View file

@ -9,7 +9,7 @@ from pycuda.compiler import SourceModule
import numpy as np
from ktransformers.operators.linear import KTransformersLinear, KLinearMarlin
from ktransformers.operators.experts import KTransformersExperts, KExpertsTorch
from ktransformers.util.custom_gguf import GGUFLoader, dequantize_q4_k_gpu, dequantize_q4_k
from ktransformers.util.custom_loader import GGUFLoader, dequantize_q4_k_gpu, dequantize_q4_k
import torch
import KTransformersOps
torch.set_default_dtype(torch.bfloat16)