Commit 3e69319

authored

llama : update llama_decode_internal ref [no ci] (ggml-org#11840)

This commit updates the comment in llama_kv_cache.h to reflect the change of the function name from llama_decode_internal to llama_decode_impl.

1 parent a394039 commit 3e69319Copy full SHA for 3e69319

File tree

-1

lines changed

-1

lines changed

Lines changed: 1 addition & 1 deletion

Original file line number	Diff line number	Diff line change
`@@ -37,7 +37,7 @@ struct llama_kv_cache {`
`37`	`37`	`bool can_shift = false;`
`38`	`38`
`39`	`39`	`// Note: The value of head isn't only used to optimize searching`
`40`		`- // for a free KV slot. llama_decode_internal also uses it, so it`
	`40`	`+ // for a free KV slot. llama_decode_impl also uses it, so it`
`41`	`41`	`// cannot be freely changed after a slot has been allocated.`
`42`	`42`	`uint32_t head = 0;`
`43`	`43`	`uint32_t size = 0;`

Comments

(0)