-
Hi @marella
Have you seen the new GGCC model format of ggllm.cpp? This significantly improves the quality of its Falcon model support. There is also improvements to performance.
But it is a ne…
-
The main llama.cpp has been updated to support GPUs on Mac's with the following flag (tested on my system):
`LLAMA_METAL=1 make -j && ./main -m /Downloads/guanaco-65B.ggmlv3.q4_0.bin -p "I believe …
-
I can load a static PDB file in NGL, but how can I load the associated DCD trajectory data, so I can play the animation in the browser? I only saw an example online with a gromacs file that had both t…
-
Hello, I have pulled today and build on windows using:
```bash
cmake -DLLAMA_CUBLAS=1
cmake --build . --config Release
```
then
```bash
$ ./main.exe -t 6 -ngl 18 -m ../../../models/gpt4-x…
-
Explain below
-
### Describe the feature you'd like to request
In the normal "T3-Stack" there is a postinstall command in package.json that pushes the prism database. Is this also possible with "T3-Turbo"?
### Desc…
-
## Summary
We now support resolving the hostnames after a certain number of failures again, using the `-r` flag.
It is beneficial to report the changes and time of them to our users. For instan…
-
Support for Metal GPU acceleration on macOS (and I assume iOS) just merged in llama.cpp master: https://github.com/ggerganov/llama.cpp/pull/1642
It would be great if this could also be employed fro…
-
I tested Command R Plus on 4 L20 cards with maximum 64K context, with 64 layers offloaded to GPU, 16 layers per card.
My prompt is relatively large, it costs around 50K tokens. During the prefill pha…
-
Hi,
I recently discovered this project and I kinda love it - it is quite customizable and allows me to create similar notification center that I had on MacOS and that I miss 🙂 I recently switched f…