 rdms
|
0a10f926c1
|
Timing analysis for the separate processing steps, also GPU -> CPU transfer
|
2025-12-14 11:02:12 +01:00 |
|
|
rdms
|
8ffd5dd122
|
PyTorch experiments
|
2025-12-13 22:50:19 +01:00 |
|
|
rdms
|
4d25d9c679
|
For AI embedding model timing checks
|
2025-12-13 22:28:55 +01:00 |
|
|
rdms
|
39ee9c3b92
|
Tried fix for gpt-oss-20b but still OOM
|
2025-11-28 22:23:05 +01:00 |
|
|
rdms
|
9b3d4e40e2
|
Qwen3-VL mode working; /unload; normal model loading times
|
2025-11-28 21:29:07 +01:00 |
|
|
rdms
|
21d7ab4a2c
|
ai-model.py with LLMs and embedding models
|
2025-11-28 18:00:48 +01:00 |
|