 Diego Devesa
|
27ebfcacba
llama : do not crash if there is no CPU backend (#13395)
|
hai 8 meses |
 Georgi Gerganov
|
833e2b7409
model : print tensor size during load (#12711)
|
hai 10 meses |
|
Diego Devesa
|
e0e912f49b
llama : add option to override model tensor buffers (#11397)
|
hai 10 meses |
 jklincn
|
e39e727e9a
llama : use LLM_KV_GENERAL_FILE_TYPE instead of gguf_find_key (#12672)
|
hai 10 meses |
 lexasub
|
a5203b4465
llama : minor fixes for up llama load model speed (#11448)
|
hai 1 ano |
 Xuan Son Nguyen
|
681149ced2
llama : add `llama_model_load_from_splits` (#11255)
|
hai 1 ano |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
hai 1 ano |
 Johannes Gäßler
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
hai 1 ano |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
hai 1 ano |
