Bodhi
Bodhi
Maybe try this one: https://www.npmjs.com/package/babel-plugin-transform-imports
Seems still broken for Windows with ```1.12.18``` install script?: ``` PS C:\windows\system32> (New-Object System.Net.WebClient).DownloadString("https://raw.githubusercontent.com/solo-io/gloo/v1.12.18/projects/gloo/cli/install.ps1") | iex Invoke-WebRequest : A positional parameter cannot be found that accepts argument 'https://api.github.com/repos/solo-io/gloo/releases'. At line:19...
Hello, It seems still not using the Metal/GPU at all on Mac/M1 with `BUILD_TYPE=metal`: After building the LocalAI on my **Mac/M1** with **master** branch: ``` make clean && make BUILD_TYPE=metal...
Hello, Seems it's supporting vllm now: https://github.com/triton-inference-server/tutorials/blob/main/Quick_Deploy/vLLM/README.md#deploying-a-vllm-model-in-triton But can we use the vllm OpenAI APIs ? Thanks a lot
Thank you for the clearance~~ though I think we could simply adapte the vLLM `vllm.entrypoints.openai.api_server` to the [triton http endpoint](https://github.com/triton-inference-server/server/blob/main/docs/protocol/extension_generate.md#httprest).
+1 that would be so awesome :+1:
Seems gpt4all isn't using GPU on Mac(m1, metal), and is using lots of CPU. Not sure for the latest release.
sigh... cypress makes simple things complex
As a `MooreThreads` GPU user, really looking forward for the ollama official support for MT GPUs.
Hi @JohannesGaessler , @ggerganov , @slaren , @yeahdongcn , Can you please help review this PR ? Thanks a lot.