llama : fix kv_cache n init (close #1903)

This commit is contained in:
Georgi Gerganov
2023-06-17 19:30:22 +03:00
parent d005fe3f4f
commit 6c1607e1dc
3 changed files with 4 additions and 0 deletions

1
.gitignore vendored
View File

@@ -34,6 +34,7 @@ models/*
/perplexity
/embedding
/train-text-from-scratch
/simple
/benchmark-matmult
/vdot
/server