-
i tried to install the llama 30B model and its not working alpaca 30B else (but i dont want it)
start with your questions
Operating System: Windows
CPU: AMD Ryzen 5 2600
Version of Dalai: Docker
…
-
### What is the issue?
Hi,
I noticed previous out of memory error fix at version 0.1.45-rc3. [https://github.com/ollama/ollama/issues/5113].
```
ollama run deepseek-coder-v2
```
Now I…
-
i think it's this part, how to disable etc?
GGML_ASSERT: /usr/local/src/go-llama.cpp/llama.cpp/ggml-cuda.cu:6642: src0->type == GGML_TYPE_F16
```
.................................................…
-
## 概要
READMEがCformersのままなので、vsimに合わせたREADMEを新たに書きたい。
## 要件
- README.mdをvsimの説明に置き換える
- Cformersとggmlをベースにしていることを明記
- ライセンス明記
-
I have a ROCm compiled with support for both the discrete GPU and the iGPU, but with `HIP_VISIBLE_DEVICES` set to `0` to ensure only the discrete GPU is considered (the iGPU is just for experimenting,…
-
Currently the llama.cpp and ggml is not default compiled with GPU support, need to build GPU supported version.
-
### Feature request
plug in to
https://github.com/lmstudio-ai/model-catalog
seems like this is all ggml format.
https://github.com/lmstudio-ai/model-catalog/blob/main/catalog.json
### Motiv…
-
[This commit](https://github.com/ggerganov/whisper.cpp/commit/2948c740a2bf43190b8e3badb6f1e147f11f96d1) breaks the compatibility with older CUDA versions, presumably < 11.1.
The culprit is `cudaHo…
-
I see in some places in the codebase the implicit assumption that a tensor's memory is contiguous, without any checks/asserts.
For example "ggml_metal_set_tensor" (get_tensor as well) has:
`memcpy((…
-
**LocalAI version:**
cc31c58235496ad7b703b55096172efb1e37feb8
**Environment, CPU architecture, OS, and Version:**
`Linux 6.1.31_1 #1 SMP PREEMPT_DYNAMIC Wed May 31 05:53:37 UTC 2023 x86_64 GN…