abetlen / abetlen/llama-cpp-python

ggml_new_tensor_impl: not enough space in the context's memory pool

未关闭
#585 11 条评论 1 个 reaction 已指派 0 人 在 GitHub 查看
llama.cpp
主要语言
Python
星标
10.6k
派生
1.4k
PR 合并指标
PR 指标待抓取

描述

I believe this is an **llma-cpp-python** issue, please refer to:

[https://github.com/PromtEngineer/localGPT/issues/349#issuecomment-1668891109](https://github.com/PromtEngineer/localGPT/issues/349#issuecomment-1668891109)

I'm trying to run [localGPT](https://github.com/PromtEngineer/localGPT) with **CUDA 12.2** .
but obtained this **ERROR** message:

```console
......
ggml_new_tensor_impl: not enough space in the context's memory pool (needed 18682928, available 10485760)
```

Does it have something to do with [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) with **CUDA 12.2** .

贡献指南

打开贡献指南

评估

这个 Issue 还没有评估数据。

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。