vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-13 00:29:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

support glm4moe

Browse source
This commit is contained in:
djw 2025-07-25 17:22:20 +00:00
parent 1677e90092
commit d03d92ba53
31 changed files with 2265 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ktransformers/server/balance_serve/sched_rpc.py
View file

@ -10,7 +10,7 @@ current_file_path = os.path.abspath(__file__)
# sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", ".."))
import pickle
import argparse
from ktransformers.server.balance_serve.settings import sched_ext, create_sched_settings, create_sched_settings_qwen2moe, create_sched_settings_qwen3moe
from ktransformers.server.balance_serve.settings import sched_ext, create_sched_settings, create_sched_settings_qwen2moe, create_sched_settings_qwen3moe, create_sched_settings_glm4moe, create_sched_settings_smallthinker
@ -213,6 +213,10 @@ if __name__ == '__main__':
settings = create_sched_settings_qwen2moe(main_args)
elif main_args.architectures == "Qwen3MoeForCausalLM":
settings = create_sched_settings_qwen3moe(main_args)
elif main_args.architectures == "Glm4MoeForCausalLM":
settings = create_sched_settings_glm4moe(main_args)
elif main_args.architectures == "SmallThinkerForCausalLM":
settings = create_sched_settings_smallthinker(main_args)
else:
settings = create_sched_settings(main_args)
start_server(settings, main_args)