conda-forge / conda-forge/llama.cpp-feedstock

[Feature Request]: Add WoA CUDA ARM 64 builds

Open
#137 0 comments 0 reactions 0 assignees View on GitHub
question
Dominant language
No language data
Stars
6
Forks
18
Avg merge
13h 42m
Merged PRs (30d)
4

Description

### Comment:

llama.cpp publishes CUDA builds for WoA as part of their releases for some time now: https://github.com/ggml-org/llama.cpp/releases/tag/b10655

I think publishing similar builds via conda-forge would be a nice feature addition :)

Contributor guide

Open the contributing guide

Research direction

No files or tests are named. Start by comparing the feedstock's current release setup with the linked llama.cpp b10655 release, then identify what is needed for WoA ARM64 CUDA builds; done means comparable builds are published through conda-forge.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
build-system
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.