Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix routing through relay, default network RPS, --token, logging, readme #399

Merged
merged 10 commits into from
Jul 22, 2023
Merged

Fix routing through relay, default network RPS, --token, logging, readme #399

Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
f150932
Hide GeneratorExit in _iterate_inference_steps()
borzunov Jul 21, 2023
5508735
Update README.md
borzunov Jul 22, 2023
16fa4f9
Update README.md
borzunov Jul 22, 2023
519d6b7
Use .from_pretrained(..., use_auth_token=token) instead of token=token
borzunov Jul 22, 2023
9c57533
Update README.md
borzunov Jul 22, 2023
09d3d18
Use default network speed 25 Mbit/s
borzunov Jul 22, 2023
1c1c440
Apply relay penalty in max-throughput routing
borzunov Jul 22, 2023
d35e919
Update readme
borzunov Jul 22, 2023
16b9ff3
Replace RPS with "tokens/sec per block" in logs
borzunov Jul 22, 2023
3d7bfce
Increase default expiration
borzunov Jul 22, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Update readme
  • Loading branch information
@borzunov
borzunov committed Jul 22, 2023
commit d35e919511c97e2477ed16dee0a7f4c9ff011970
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ Run these commands in an [Anaconda](https://www.anaconda.com) env (requires Linu

```bash
conda install pytorch pytorch-cuda=11.7 -c pytorch -c nvidia
pip install --upgrade petals
pip install git+https://github.com/bigscience-workshop/petals
python -m petals.cli.run_server enoch/llama-65b-hf --adapters timdettmers/guanaco-65b
```

Expand Down Expand Up @@ -101,7 +101,7 @@ Here's how to install Petals with [Anaconda](https://www.anaconda.com/products/d

```bash
conda install pytorch pytorch-cuda=11.7 -c pytorch -c nvidia
pip install --upgrade petals
pip install git+https://github.com/bigscience-workshop/petals
```

If you don't use Anaconda, you can install PyTorch in [any other way](https://pytorch.org/get-started/locally/). If you want to run models with 8-bit weights, please install PyTorch with CUDA 11.x or newer for compatility with [bitsandbytes](https://github.com/timDettmers/bitsandbytes).
Expand Down
Loading