| .. |
|
CMakeLists.txt
|
6171c9d258
Add Jinja template support (#11016)
|
1 gadu atpakaļ |
|
llama-adapter.cpp
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 gadu atpakaļ |
|
llama-adapter.h
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 gadu atpakaļ |
|
llama-arch.cpp
|
6171c9d258
Add Jinja template support (#11016)
|
1 gadu atpakaļ |
|
llama-arch.h
|
6171c9d258
Add Jinja template support (#11016)
|
1 gadu atpakaļ |
|
llama-batch.cpp
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 gadu atpakaļ |
|
llama-batch.h
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 gadu atpakaļ |
|
llama-chat.cpp
|
ec7f3ac9ab
llama : add support for Deepseek-R1-Qwen distill model (#11310)
|
1 gadu atpakaļ |
|
llama-chat.h
|
d9feae1c06
llama-chat : add phi 4 template (#11148)
|
1 gadu atpakaļ |
|
llama-context.cpp
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 gadu atpakaļ |
|
llama-context.h
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 gadu atpakaļ |
|
llama-cparams.cpp
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 gadu atpakaļ |
|
llama-cparams.h
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 gadu atpakaļ |
|
llama-grammar.cpp
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 gadu atpakaļ |
|
llama-grammar.h
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 gadu atpakaļ |
|
llama-hparams.cpp
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 gadu atpakaļ |
|
llama-hparams.h
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 gadu atpakaļ |
|
llama-impl.cpp
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
1 gadu atpakaļ |
|
llama-impl.h
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 gadu atpakaļ |
|
llama-kv-cache.cpp
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 gadu atpakaļ |
|
llama-kv-cache.h
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 gadu atpakaļ |
|
llama-mmap.cpp
|
90d987b105
mmap: add include for cerrno (#11296)
|
1 gadu atpakaļ |
|
llama-mmap.h
|
ae2f606bb5
mmap : fix fileno macro clash (#11076)
|
1 gadu atpakaļ |
|
llama-model-loader.cpp
|
681149ced2
llama : add `llama_model_load_from_splits` (#11255)
|
1 gadu atpakaļ |
|
llama-model-loader.h
|
681149ced2
llama : add `llama_model_load_from_splits` (#11255)
|
1 gadu atpakaļ |
|
llama-model.cpp
|
6171c9d258
Add Jinja template support (#11016)
|
1 gadu atpakaļ |
|
llama-model.h
|
667d72846c
rpc : early register backend devices (#11262)
|
1 gadu atpakaļ |
|
llama-quant.cpp
|
681149ced2
llama : add `llama_model_load_from_splits` (#11255)
|
1 gadu atpakaļ |
|
llama-quant.h
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 gadu atpakaļ |
|
llama-sampling.cpp
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 gadu atpakaļ |
|
llama-sampling.h
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 gadu atpakaļ |
|
llama-vocab.cpp
|
ec7f3ac9ab
llama : add support for Deepseek-R1-Qwen distill model (#11310)
|
1 gadu atpakaļ |
|
llama-vocab.h
|
08f10f69c3
llama : remove notion of CLS token (#11064)
|
1 gadu atpakaļ |
|
llama.cpp
|
667d72846c
rpc : early register backend devices (#11262)
|
1 gadu atpakaļ |
|
unicode-data.cpp
|
458367a906
server : better security control for public deployments (#9776)
|
1 gadu atpakaļ |
|
unicode-data.h
|
a39ab216aa
llama : reduce compile time and binary size (#9712)
|
1 gadu atpakaļ |
|
unicode.cpp
|
4dd34ff831
cmake : add sanitizer flags for llama.cpp (#11279)
|
1 gadu atpakaļ |
|
unicode.h
|
08ea539df2
unicode : improve naming style (#10838)
|
1 gadu atpakaļ |
Olivier Chafik
6171c9d258
Add Jinja template support (#11016)