mirror of
https://github.com/ollama/ollama
synced 2026-04-23 08:45:14 +00:00
In cases where we allocate a tensor and then fully overwrite it with copied data, it is wasteful to first zero out the memory. |
||
|---|---|---|
| .. | ||
| cache.go | ||
| causal.go | ||
| causal_test.go | ||
| encoder.go | ||
| wrapper.go | ||