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

Merge pull request #1276 from kvcache-ai/support_load_safetensor
Some checks failed
Book-CI / test (push) Has been cancelled
Details
Deploy / deploy (macos-latest) (push) Has been cancelled
Details
Deploy / deploy (ubuntu-latest) (push) Has been cancelled
Details
Deploy / deploy (windows-latest) (push) Has been cancelled
Details

Browse source 
support safetensor load, delete architectures argument
This commit is contained in:
wang jiahao 2025-05-12 11:10:26 +08:00 • committed by GitHub
commit 8456222852
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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,