vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-05-01 21:21:12 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

add kt-kernel

Browse source
This commit is contained in:
Atream 2025-10-12 05:13:00 +00:00
parent a064cc8525
commit 4c5fcf9774
188 changed files with 59126 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

16
kt-kernel/cuda/test_dequant.py Normal file
View file

@ -0,0 +1,16 @@
import os
import sys
sys.path.insert(0,"/home/zbx/ktransformers")
from ktransformers.util.custom_loader import GGUFLoader
import torch
gguf_loader_1 = GGUFLoader("/mnt/data/model/DeepseekV3-q4km-gguf")
gguf_loader_2 = GGUFLoader("/mnt/data/chenht/model/gguf_for_ktransformers/DeepSeek-V3-bf16/")
torch.set_default_dtype(torch.bfloat16)
tensor_1 = gguf_loader_1.load_gguf_tensor("blk.0.attn_kv_a_mqa.weight", "cuda")
tensor_2 = gguf_loader_2.load_gguf_tensor("blk.0.attn_kv_a_mqa.weight", "cuda")
print(tensor_1[0, -64:])
print(tensor_2[0, -64:])