ochafik/llama.cpp

Pull Requests Commits

Merge remote-tracking branch 'origin/master' into chat-cleanups

Olivier Chafik committed 1 year ago

9a854391

server : add TEI API format for /rerank endpoint (#11942)

ngxson committed 1 year ago

Verified 63ac1285

scripts: corrected encoding when getting chat template (#11866) (#11907)

MoonRide303 committed 1 year ago

Verified 5137da7b

docs : Fix duplicated file extension in test command (#11935)

xiaobing318 committed 1 year ago

Verified 09aaf4f1

use deleter functor for common_chat_templates_ptr

Olivier Chafik committed 1 year ago

fd2b8e10

build common_chat_templates_ptr earlier

Olivier Chafik committed 1 year ago

d2969b87

chat.{hpp -> h}

Olivier Chafik committed 1 year ago

7ddb4540

have common_chat_templates_init return a unique_ptr

Olivier Chafik committed 1 year ago

da0982a0

CUDA: use async data loading for FlashAttention (#11894)

JohannesGaessler committed 1 year ago

Verified 73e2ed3c

update release requirements (#11897)

netrunnereve committed 1 year ago

Verified f7b1116a

server : fix divide-by-zero in metrics reporting (#11915)

aviallon committed 1 year ago

Verified c4d29baf

vulkan: implement several ops relevant for ggml_opt (#11769)

remyoudompheng committed 1 year ago

Verified 2eea03d8

Update chat.hpp

ochafik committed 1 year ago

9d62f62f

add missing <regex> include to test-chat-template

ochafik committed 1 year ago

55a76143

alternative fix for gcc c vs. c++ weirdness

ochafik committed 1 year ago

f999ff56

tiny fix: somehow llama_token being defined in an extern c makes it less than a c++ typedef

ochafik committed 1 year ago

a58b9e5e

Add missing <optional> include to chat.cpp

ochafik committed 1 year ago

2f2f0fa1

rm trailing spaces

ochafik committed 1 year ago

dd5ef85f

ochafik committed 1 year ago

5a5ed7bf

Merge remote-tracking branch 'origin/master' into chat-cleanups

ochafik committed 1 year ago

d95a17ce

fix links to prepare merge

ochafik committed 1 year ago

14210371

test & fix array message.content

ochafik committed 1 year ago

ae6b870d

Update test-chat-template.cpp

ochafik committed 1 year ago

1c6168bc

fix & test grammar & json_schema w/ & w/o --jinja

ochafik committed 1 year ago

34e4e224

tool-call: allow empty tools w/ auto + grammar

ochafik committed 1 year ago

76f5d27b

ochafik committed 1 year ago

cb31f087

add common_chat_templates_source + rehab server template logs

ochafik committed 1 year ago

ce4ccf03

fix double bos/eos jinja avoidance hack (was preventing inner bos/eos tokens)

ochafik committed 1 year ago

42b29e12

tweak test_calc_result expectations

ochafik committed 1 year ago

80c432b6

fix lints in test-chat-template.cpp

ochafik committed 1 year ago

8462a515

Older