-
Notifications
You must be signed in to change notification settings - Fork 1.7k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
鲲鹏920加载LLM报错 #3104
Labels
bug
Something isn't working
Comments
修改 config.json ,把 precision 设成 normal ,memory 设成low 试下 |
不行,还是同样的错误
|
呃,有 crash 堆栈么? 一开始的 The device supports: 打印是什么? |
先更新到 3.0.1 试试,有可能是 prepare 的 bug |
emmmmm不太行,已经更新了
device supports 打印内容:
|
可能是 cpu feature 计算结果有问题。系统的 aux 判断不准,可以手动修改 source/backend/cpu/CPURuntime.cpp 末尾,把 i8mm / dot 设成 false 试试 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
平台(如果交叉编译请再附上交叉编译目标平台):
Platform(Include target platform as well if cross-compiling): 鲲鹏920
-- MNN BUILD INFO:
-- System: Linux
-- Processor: aarch64
-- Version: 3.0.0
-- Metal: OFF
-- OpenCL: OFF
-- OpenGL: OFF
-- Vulkan: OFF
-- ARM82: ON
-- KleidiAI: OFF
-- oneDNN: OFF
-- TensorRT: OFF
-- CoreML: OFF
-- NNAPI: OFF
-- CUDA: OFF
-- OpenMP: OFF
-- BF16: OFF
-- ThreadPool: ON
-- Hidden: TRUE
-- Build Path: /root/Qwen2-VL-7B-Instruct-MNN/MNN/build
-- CUDA PROFILE: OFF
Github版本:3.0
编译方式: 源码编译
编译日志:
Build Log:
运行命令:
运行日志
The text was updated successfully, but these errors were encountered: