llama.cpp
llama : cache llama_token_to_piece
#7587
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
4
Changes
View On
GitHub
llama : cache llama_token_to_piece
#7587
mofosyne
merged 4 commits into
master
from
gg/cache-token-to-piece
ggerganov
force pushed
from
92b88a04
to
3e5d281c
1 year ago
mofosyne
added
Review Complexity : Low
ggerganov
requested a review
from
ochafik
1 year ago
ggerganov
requested a review
from
HanClinto
1 year ago
llama : cache llama_token_to_piece
9964cd02
ggerganov
force pushed
from
3e5d281c
to
9964cd02
1 year ago
ggerganov
added
merge ready
HanClinto
commented on 2024-05-29
HanClinto
commented on 2024-05-29
HanClinto
commented on 2024-05-29
llama : use vectors and avoid has_cache
21ccd645
llama : throw on unknown tokenizer types
1494a184
HanClinto
commented on 2024-05-29
HanClinto
commented on 2024-05-29
HanClinto
commented on 2024-05-29
llama : print a log of the total cache size
8a8f8b95
ggerganov
force pushed
from
5069b93b
to
8a8f8b95
1 year ago
HanClinto
approved these changes on 2024-05-29
ochafik
approved these changes on 2024-05-30
mofosyne
merged
5921b8f0
into master
1 year ago
Login to write a write a comment.
Login via GitHub
Reviewers
ochafik
HanClinto
Assignees
No one assigned
Labels
Review Complexity : Low
merge ready
Milestone
No milestone
Login to write a write a comment.
Login via GitHub