mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-11-05 01:07:28 +00:00
[GH-ISSUE #958] [Feature] deepseek-r1 671b太大了,有deepseek-v2-lite成功安装的流程吗? #679
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
kvcache-ai/ktransformers#679
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @blockcloud on GitHub (Mar 22, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/958
检查清单
需求背景
由于r1 671b太大,需要的资源太多,就尝试允许v2-lite版本,在modelscope上下载了gguf文件
DeepSeek-V2-Lite-Chat-Q4_K_M.gguf
结果运行的时候,提示缺少token_embd.weight in GGUF file!文件
File "/workspace/ktransformers/ktransformers/util/utils.py", line 78, in load_cur_state_dict raise Exception(f"can't find {translated_key} in GGUF file!") Exception: can't find token_embd.weight in GGUF file!这个如何解决呢?
相关资源
No response
@tsdcz commented on GitHub (Mar 23, 2025):
可以,我就跑的这个版本,参考文档把参数文件下载全了就能运行,这是我本地5700X+1080跑的结果

@tsdcz commented on GitHub (Mar 23, 2025):
python3 local_chat.py --gguf_path /models/deepseek-v2-lite-chat.Q8_0_gguf/ --model_path /models/deepseek-v2-lite-chat_info/ --optimize_config_path /models/DeepSeek-V2-Lite-Chat.yaml --port 10002 --cpu_infer 14
我跑的是Q8,显存占用2G多,运行时GPU占用不到20%
@blockcloud commented on GitHub (Mar 24, 2025):
@blockcloud commented on GitHub (Mar 24, 2025):
你好,完整的模型文件名可以分享一下吗?我去下载部署,还有,这个模型内存占用有多少呢?