vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-16 10:09:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

optimize gguf dequant, save mem, support Q2_K

Browse source 
use marlin for lm_head, lm_head only calc last token for prefill
extend context window to 19K for DeepSeek-V3/R1 within 24GB VRAM
This commit is contained in:
Atream 2025-02-22 06:13:01 +00:00
parent 7e1fe256c8
commit 5ec33d046d
27 changed files with 435 additions and 259 deletions
Download patch file Download diff file Expand all files Collapse all files

16
ktransformers/ktransformers_ext/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_gguf 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:])