vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-09 13:55:27 +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/operators/models.py
View file

@ -58,7 +58,7 @@ from transformers.models.qwen2_moe.configuration_qwen2_moe import Qwen2MoeConfig
from ktransformers.models.configuration_llama import LlamaConfig
from ktransformers.operators.base_operator import BaseInjectedModule
from ktransformers.util.utils import InferenceState, get_compute_capability
from ktransformers.util.custom_gguf import GGUFLoader
from ktransformers.util.custom_loader import GGUFLoader
from transformers.configuration_utils import PretrainedConfig
from ktransformers.models.modeling_llama import (
LlamaDecoderLayer,