Commit Graph

16 Commits

Author SHA1 Message Date
a6c118322d vbgn 2025-12-24 01:38:17 -05:00
29a3e6a8a7 gyuh 2025-12-24 01:36:59 -05:00
a252079767 ty 2025-12-24 01:36:21 -05:00
c92bfe2379 ftgy 2025-12-24 01:33:53 -05:00
ad49c0634d bbhjbh 2025-12-24 01:31:31 -05:00
1a329f54bd fix device card 2025-12-24 01:30:07 -05:00
972b1cec61 Fixed formatting 2025-12-24 01:27:24 -05:00
41d68a8214 Ollama debug 2025-12-24 01:24:16 -05:00
a5c2d494a8 Fix device tree 2025-12-24 01:22:14 -05:00
05374e93a7 Fix env variables 2025-12-24 01:18:47 -05:00
49d8d4362e Fix eGPU Init 2025-12-24 01:16:53 -05:00
ed69658364 Correct bind mounts for P52 2025-12-24 00:55:53 -05:00
aa2a23091d Correct network name 2025-12-24 00:53:24 -05:00
9323a0624a Add web ui's 2025-12-24 00:50:47 -05:00
8095c7b951 Removed name 2025-12-24 00:39:26 -05:00
1cf853ac46 feat(ollama): add docker swarm configuration for rocm gpu support
Introduce a new compose.yml to deploy Ollama with AMD GPU hardware acceleration on Docker Swarm.

- Uses the ROCm-enabled Ollama image.
- Mounts necessary GPU devices (/dev/kfd and /dev/dri) with root permissions for hardware access.
- Sets HSA_OVERRIDE_GFX_VERSION to 10.3.0 to support Navi 21 (6900 XT) cards.
- Configures persistent storage on local SSD and integrates with an external proxy network.
- Includes deployment constraints to target nodes labeled with GPUs.
2025-12-24 00:37:23 -05:00