search

b4rtaz / distributed-llama

Tensor parallelism is all you need. Run LLMs on weak devices or make powerful devices even more powerful by distributing the workload and dividing the RAM usage.
MIT License
1.02k stars 68 forks source link

Request: Community Discord? #77

Closed unclemusclez closed 1 month ago

unclemusclez commented 1 month ago

I'll help out and moderate if necessary. It would be nice to keep in contact with development, and the project seems to be gaining traction.

I didn't feel it was right to start it without a blessing, and I don't know if one already exists.

Thanks

b4rtaz commented 1 month ago

https://discord.gg/7M4BXkM4 Later I'll add this to README.md.