GPU builds of the llama-rpc image (CUDA, Vulkan)

Open
#28 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
30/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
docker, github-actions

Research direction

Start with the image build in .github/workflows/llama-rpc.yml, then find where llama-distributed reads the GPU inventory and chooses a worker's variant. Done means CUDA and Vulkan tags are built, the right tag is picked per machine, and GPU workers are marked with "gpu": true. The issue does not say how a worker reports its GPU, so check that first.

Written by the indexing model from the issue text.

Description

ai roadmap

ghcr.io/a-hackers-guide/llama-rpc is CPU-only today. Add CUDA and Vulkan variants (tags like b12019-cuda, b12019-vulkan) built in .github/workflows/llama-rpc.yml, and let llama-distributed pick the variant per machine from its GPU inventory. Mark GPU workers with "gpu": true once the image can use them.

Dominant language
Go
Stars
1
Forks
0
Avg merge
12m
Merged PRs (30d)
2

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from A-Hackers-Guide/sys1

All issues in A-Hackers-Guide/sys1

Similar issues

More Go issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.