13 Commits

Author	SHA1	Message	Date
abysssol	59a240579c	ollama: test that rocm and cuda build successfully	2024-02-25 15:57:58 -05:00
abysssol	70e834c19b	ollama: refactor	2024-02-25 15:57:58 -05:00
abysssol	c75dd8bff7	ollama: 0.1.24 -> 0.1.26	2024-02-25 13:35:23 -05:00
abysssol	30a7446a15	ollama: add support for gpu acceleration	2024-02-16 16:23:25 -05:00
abysssol	828b4dc30e	ollama: 0.1.17 -> 0.1.24 ... Remove outdated patches and substitution of llama.cpp server. Patch source build script to remove git. Ollama's `go generate` script assumes the source is an initialized git repository, which it is not in nix. So, remove usage of `git` and replace it with `patch`. Also replace call to `g++` with `$CXX`. Run `go generate` to build dependencies using ollama's custom build script.	2024-02-16 16:23:25 -05:00
happysalada	cdbfd046bf	ollama: 0.1.11 -> 0.1.17	2023-12-19 05:16:15 +01:00
Rafael Fernández López	0e23cb377f	ollama: 0.1.7 -> 0.1.11	2023-11-22 12:45:45 -06:00
Enno Richter	ea3a7c56fd	ollama: 0.0.17 -> 0.1.7, use llama-cpp	2023-11-02 09:31:58 +01:00
R. Ryantm	220c035420	ollama: 0.0.15 -> 0.0.17	2023-09-01 04:05:05 +00:00
R. Ryantm	489add96d5	ollama: 0.0.14 -> 0.0.15	2023-08-21 04:00:51 +00:00
R. Ryantm	e2c6a2826e	ollama: 0.0.13 -> 0.0.14	2023-08-16 09:26:34 +00:00
R. Ryantm	2ac544bd50	ollama: 0.0.12 -> 0.0.13	2023-08-06 21:44:54 +00:00
Mostly Void	12ac911bf8	ollama: init at 0.0.12	2023-08-01 01:31:27 +03:00