 Xuan-Son Nguyen
|
bd3f59f812
cmake : enable curl by default (#12761)
|
9 meses atrás |
 Michał Moskal
|
ff227703d6
sampling : support for llguidance grammars (#10224)
|
11 meses atrás |
 Olivier Chafik
|
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
|
11 meses atrás |
 Georgi Gerganov
|
4dd34ff831
cmake : add sanitizer flags for llama.cpp (#11279)
|
1 ano atrás |
 Johannes Gäßler
|
081b29bd2a
tests: add tests for GGUF (#10830)
|
1 ano atrás |
 Diego Devesa
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
1 ano atrás |
|
Diego Devesa
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 ano atrás |
|
Georgi Gerganov
|
84274a10c3
tests : remove test-grad0
|
1 ano atrás |
 Max Krasnyansky
|
0226613853
threadpool : skip polling for unused threads (#9461)
|
1 ano atrás |
|
Georgi Gerganov
|
6262d13e0b
common : reimplement logging (#9418)
|
1 ano atrás |
 Xuan Son Nguyen
|
1b9ae5189c
common : refactor arg parser (#9308)
|
1 ano atrás |
|
Georgi Gerganov
|
e093dd2382
tests : re-enable tokenizer tests (#8611)
|
1 ano atrás |
|
Georgi Gerganov
|
0c27e6f62e
ggml : fix loongson compile warnings (#7537)
|
1 ano atrás |
 Haoxiang Fei
|
f99e1e456e
llama : lookup word in vocab before doing BPE merges (#7193)
|
1 ano atrás |
 Ren Xuancheng
|
229ffff872
llama : add BPE pre-tokenization for Qwen2 (#7114)
|
1 ano atrás |
 DAN™
|
889bdd7686
command-r : add BPE pre-tokenization (#7063)
|
1 ano atrás |
|
Georgi Gerganov
|
92139b90af
tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
|
1 ano atrás |
|
Georgi Gerganov
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
1 ano atrás |
|
Olivier Chafik
|
7593639ce3
`main`: add --json-schema / -j flag (#6659)
|
1 ano atrás |
 Clint Herron
|
57dd02c44b
Tests: Added integration tests for GBNF parser (#6472)
|
1 ano atrás |
|
Olivier Chafik
|
5b7b0ac8df
json-schema-to-grammar improvements (+ added to server) (#5978)
|
1 ano atrás |
|
Xuan Son Nguyen
|
11b12de39b
llama : add llama_chat_apply_template() (#5538)
|
1 ano atrás |
 crasm
|
413e7b0559
ci : add model tests + script wrapper (#4586)
|
2 anos atrás |
|
Georgi Gerganov
|
c918fe8dca
metal : create autorelease pool during library build (#4970)
|
2 anos atrás |
 Cuong Trinh Manh
|
97bbca6e85
cmake : fix ld warning duplicate libraries libllama.a (#4671)
|
2 anos atrás |
 manikbhandari
|
ea5497df5d
gpt2 : Add gpt2 architecture integration (#4555)
|
2 anos atrás |
|
Georgi Gerganov
|
fe680e3d10
sync : ggml (new ops, tests, backend, etc.) (#4359)
|
2 anos atrás |
 Galunid
|
36eed0c42c
stablelm : StableLM support (#3586)
|
2 anos atrás |
|
Galunid
|
daab3d7f45
Add more tokenizer tests (#3742)
|
2 anos atrás |
 goerch
|
9e70cc0322
Add test for MPT tokenization (#3728)
|
2 anos atrás |
