Ricardo Jesus Malagon Jerez
Ricardo Jesus Malagon Jerez
Maybe this hint can help you. My local network is IPV6 only. Sent with [ProtonMail](https://protonmail.com) Secure Email. ‐‐‐‐‐‐‐ Original Message ‐‐‐‐‐‐‐ On Sunday, January 24, 2021 6:20 PM, Pavlo Buidenkov...
My Fedora 35 server already upgrade to 1.8.5. My system has libcrypto.so.10. Give a look at your repos, could be something tangled there.
Yes. I confirm this. Something is missing there because you can add manually the correspondent IP6 address to the tun interface with the native CLI tools, and it works. I...
+1. After ~20 minutes headscale is stuck with timeouts while updating nodes.
After carefully checks about my headscale VMs stats, I found that is very ram sensitive. In a serve ~200+ nodes with a 2Gb RAM / 4 CPU VM. Sometimes, headscale...
I am wrong on this, headscale sometimes gets stuck, even with enough memory and CPU. Usually, it gets stuck on multiples "waiting for update on stream channel". I set up...
> [0.23.0-alpha2](https://github.com/juanfont/headscale/releases/tag/v0.23.0-alpha2) addresses a series of issues with node synchronisation, online status and subnet routers, please test this release and report back if the issue still persist. Hi, the stability...
rerank and colbert too. https://huggingface.co/mixedbread-ai/mxbai-colbert-large-v1
rerank and colbert would be wonderful, compliment embedding nicely on RAG. Good open models exist https://huggingface.co/mixedbread-ai/mxbai-rerank-large-v1 https://huggingface.co/mixedbread-ai/mxbai-colbert-large-v1 Does llama.cpp support this?
I bring this as an idea on llama.cpp discussions. https://github.com/ggerganov/llama.cpp/discussions/8216