vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-15 01:29:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

GLM4 and SmallThinker

Browse source
This commit is contained in:
qiyuxinlin 2025-07-25 16:56:36 +00:00
parent c7307aa0ae
commit 9e1560bb82
7 changed files with 58 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ktransformers/tests/test_speed.py
View file

@ -162,7 +162,6 @@ if __name__ == "__main__":
elif args.prompt_lens == 4096:
prompt = ktansformer_prompt1024 * 4
prompt = "介绍秦始皇"
asyncio.run(main(args.concurrent, prompt, max_tokens, model))