Max Ryabinin

One more noted issue: by default, we download a version of libp2p-daemon that is compiled for Linux. We should check the system during installation and download the precompiled daemon only...

Not sure if I need any help, since we're mostly waiting for the new bitsandbytes release

Also, remove any remaining mentions of tensor chunks from the codebase

Hi, thanks for reporting this! Can you try running some PyTorch code that is independent of Petals in your environment? For instance, any example from the transformers library: https://github.com/huggingface/transformers/tree/main/examples/pytorch

Hi @Gad1001 and @vrosca, we've just committed a fix for the SST-2 prompt tuning notebook in https://github.com/bigscience-workshop/petals/pull/343. Can you try rerunning the updated notebook from the main branch?

Hi! They are available for the previous year's iteration: https://github.com/mryab/efficient-dl-systems/tree/2023 Current ones are within YSDA's LMS (and they are in Russian anyway), but I will look into uploading them in...

Hi, thank you for your interest in this project! Right now we don't have a definite guide on running the experiments in closed-port environments, but we are working on [merging](https://github.com/learning-at-home/hivemind/pull/226)...

One small addition to @justheuristic's response: as far as I know, neither torch.distributed nor DS-Inference provide you with a full-fledged setup for running a model inference server, only the building...

Hi! To get a general idea of how many GPUs are connected to the public swarm, you can have a look at http://health.petals.ml/ (implemented [here](https://github.com/borzunov/health.petals.ml)). We might implement a more...

Hi @bionicles, Petals is a system designed specifically for inference of large models: however, it shares a lot of the underlying architecture with [SWARM Parallelism](https://arxiv.org/abs/2301.11913) (see https://github.com/yandex-research/swarm for a WIP...