ollama-for-amd/ml/backend/ggml/ggml.go at 764e199d6703d80da4d245381efa4a3a412813b2

mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-23 23:18:26 +00:00

Files

Michael Yang 764e199d67 kvcache: create cache ctx per layer

each cache layer creates and maintains its own context instead of using
a large context for all layers

2025-03-07 14:08:21 -08:00

View Raw