 Vitali Lovich
|
3e9a2860e9
llama : expose llama_model_n_head_kv in the API (#11997)
|
hai 11 meses |
 Georgi Gerganov
|
51f311e057
llama : skip loading unused tensors (#12004)
|
hai 11 meses |
|
Georgi Gerganov
|
bdcf8b6a56
cont : fix mmap flag print (#11699)
|
hai 11 meses |
|
Georgi Gerganov
|
9dd7a0390f
llama : add log about loading model tensors (#11699)
|
hai 11 meses |
 piDack
|
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)
|
hai 11 meses |
 Frank Mai
|
1d8ee06000
rpc: fix register position (#11424)
|
hai 1 ano |
 Olivier Chafik
|
6171c9d258
Add Jinja template support (#11016)
|
hai 1 ano |
|
Georgi Gerganov
|
ef6dada60c
cont : fix whitespaces (#11305)
|
hai 1 ano |
 Kyle Bruene
|
ae3c1db2f9
llama : re-add LLM_ARCH_PHIMOE (#11305)
|
hai 1 ano |
 Radoslav Gerganov
|
667d72846c
rpc : early register backend devices (#11262)
|
hai 1 ano |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
hai 1 ano |
 Molly Sophia
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
hai 1 ano |
 Pierrick Hymbert
|
f8feb4b01a
model: Add support for PhiMoE arch (#11003)
|
hai 1 ano |
|
Georgi Gerganov
|
47182dd03f
llama : update llama_model API names (#11063)
|
hai 1 ano |
|
Georgi Gerganov
|
727368c60f
llama : use LLAMA_TOKEN_NULL (#11062)
|
hai 1 ano |
 fairydreaming
|
9394bbd484
llama : Add support for DeepSeek V3 (#11049)
|
hai 1 ano |
 DAN™
|
46be942214
llama : add support for the cohere2 model architecture (#10900)
|
hai 1 ano |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
hai 1 ano |
