ollama: 0.3.5 -> 0.3.8
Diff: https://github.com/ollama/ollama/compare/v0.3.5...v0.3.8
Changelog: https://github.com/ollama/ollama/releases/tag/v0.3.8
Description of changes
Things done
- Built on platform(s)
- [ ] x86_64-linux
- [ ] aarch64-linux
- [ ] x86_64-darwin
- [ ] aarch64-darwin
- For non-Linux: Is sandboxing enabled in
nix.conf? (See Nix manual)- [ ]
sandbox = relaxed - [ ]
sandbox = true
- [ ]
- [ ] Tested, as applicable:
- NixOS test(s) (look inside nixos/tests)
- and/or package tests
- or, for functions and "core" functionality, tests in lib/tests or pkgs/test
- made sure NixOS tests are linked to the relevant packages
- [ ] Tested compilation of all packages that depend on this change using
nix-shell -p nixpkgs-review --run "nixpkgs-review rev HEAD". Note: all changes have to be committed, also see nixpkgs-review usage - [ ] Tested basic functionality of all binary files (usually in
./result/bin/) - 24.11 Release Notes (or backporting 23.11 and 24.05 Release notes)
- [ ] (Package updates) Added a release notes entry if the change is major or breaking
- [ ] (Module updates) Added a release notes entry if the change is significant
- [ ] (Module addition) Added a release notes entry if adding a new NixOS module
- [ ] Fits CONTRIBUTING.md.
Add a :+1: reaction to pull requests you find important.
Failure seems to be in the check phase due to not having a GPU to load the relevant models. Not sure how this was handled in the past.
From my attempts, it seems the unit test TestHomogeneousGPUs (in server/sched_test.go) for the ollama-server is failing somehow since 0.3.6 though nothing appears to have changed for the test. The only odd thing I see is the return (https://github.com/ollama/ollama/blob/4c4fe3f87fe1858b35bd0d41e093a0039ec4cee4/server/sched_test.go#L689) doesn't have a nil but again that's been like that for a while.
I was able to successfuly build 0.3.9 ROCm & CUDA. I can verify cuda which runs/works for me.
Someone else has to test ROCm as I don't have that GPU.