vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-10 15:29:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update rope calculation; update modeling.py; update gate for moe

Browse source
This commit is contained in:
Azure 2025-02-01 07:32:21 +00:00
parent 5a50b34627
commit f873558a89
11 changed files with 402 additions and 412 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ktransformers/local_chat.py
View file

@ -15,7 +15,7 @@ from ktransformers.server.args import ArgumentParser
from ktransformers.models.modeling_deepseek import DeepseekV2ForCausalLM
from ktransformers.models.modeling_deepseekv3 import DeepseekV3ForCausalLM
from ktransformers.models.modeling_deepseek_v3 import DeepseekV3ForCausalLM
from ktransformers.models.modeling_qwen2_moe import Qwen2MoeForCausalLM
from ktransformers.models.modeling_llama import LlamaForCausalLM
from ktransformers.models.modeling_mixtral import MixtralForCausalLM
@ -78,7 +78,7 @@ def local_chat():
else:
content += line + "\n"
if content == "":
if config.prompt_file == None or config.prompt_file == "":
if not config.prompt_file:
content = "hi"
else:
content = open(config.prompt_file, "r").read()