ollama/model
2026-05-10 14:08:57 -07:00
..
input batch: use tensors for outputs (#12185) 2025-09-15 14:33:06 -07:00
models refine implementation 2026-05-06 17:26:05 -07:00
parsers refine implementation 2026-05-06 17:26:05 -07:00
renderers misc discovery fixes, and bos handling 2026-05-10 14:08:57 -07:00
model.go runner: Remove CGO engines, use llama-server exclusively for GGML models 2026-05-06 17:26:05 -07:00