Release 0.3.7

0.3.7 (2024-07-29)

Bug Fixes

• cpp: correct validateModelChatTemplate fn (f9ed84a)

Features

• example: add Chat Template in initial message (124cb6a)

Release 0.3.6

0.3.6 (2024-07-28)

Features

• example: update json schema example (2f70192)
• support chat format (#72) (030ebaf)

Release 0.3.5

0.3.5 (2024-07-27)

Bug Fixes

• android: revert Debug comment (7972f83)
• cpp: incomplete utf-8 character (3799cf8)
• not init sampling before get embedding (#69) (1088300)

Features

• sync llama.cpp (#71) (a579ce3)

Release 0.3.3

0.3.3 (2024-07-22)

Bug Fixes

• add build for armv82 and v84 and sync llama.cpp (#67) (1942159)
• android: loadSession not taking paths with file:// (#66) (39d1e05)

Release 0.3.2

0.3.2 (2024-05-29)

Features

• sync llama.cpp (#58) (dc6a47a)

Release 0.3.0

0.3.0 (2024-04-26)

Features

• add model details in context (#52) (f2a4c53)
• android, example: disable repeat penalties by default (cf685ad)
• example: add missing commands help (4a53e68)
• migrate to new session API (725117c)

Release 0.3.0-rc.18

0.3.0-rc.18 (2024-04-25)

Features

• sync llama.cpp (#51) (0b8f9bb)
• ts: sync grammar converter (#48) (7834a73)

Release 0.3.0-rc.9

0.3.0-rc.9 (2023-12-20)

Bug Fixes

• android: use THREAD_POOL_EXECUTOR (c294171)

Features

• ios: use created dispatch_queue_t instead of main (b173d18)
• jest: add bench mock (9df745c)

Release 0.3.0-rc.8

0.3.0-rc.8 (2023-12-19)

Features

• add bench method (#35) (9d0c7df)
• sync llama.cpp (a57171e)

Release 0.3.0-rc.0

0.3.0-rc.0 (2023-10-11)

Bug Fixes

• android: default rope_freq_base / rope_freq_scale to 0 during recent breaking change (43e036e)
• cpp: incorrect num_tokens_predicted (6dd9865)

Features

• cpp: reuse llama_sample_token common util (#25) (95b4fb2)
• implement loadSession & saveSession methods (#23) (68fe09c)
• sync llama.cpp (81f9cb2)
• sync llama.cpp (#22) (8da7244)