| .. |
|
CMakeLists.txt
|
6171c9d258
Add Jinja template support (#11016)
|
hai 1 ano |
|
llama-adapter.cpp
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
hai 1 ano |
|
llama-adapter.h
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
hai 1 ano |
|
llama-arch.cpp
|
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)
|
hai 11 meses |
|
llama-arch.h
|
6171c9d258
Add Jinja template support (#11016)
|
hai 1 ano |
|
llama-batch.cpp
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
hai 1 ano |
|
llama-batch.h
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
hai 1 ano |
|
llama-chat.cpp
|
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)
|
hai 11 meses |
|
llama-chat.h
|
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)
|
hai 11 meses |
|
llama-context.cpp
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
hai 1 ano |
|
llama-context.h
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
hai 1 ano |
|
llama-cparams.cpp
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
hai 1 ano |
|
llama-cparams.h
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
hai 1 ano |
|
llama-grammar.cpp
|
c7f460ab88
`server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607)
|
hai 11 meses |
|
llama-grammar.h
|
369be5598a
llama : fix typo in llama-grammar.h [no ci] (#11816)
|
hai 11 meses |
|
llama-hparams.cpp
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
hai 1 ano |
|
llama-hparams.h
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
hai 1 ano |
|
llama-impl.cpp
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
hai 1 ano |
|
llama-impl.h
|
fef0cbeadf
cleanup: fix compile warnings associated with gnu_printf (#11811)
|
hai 11 meses |
|
llama-kv-cache.cpp
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
hai 1 ano |
|
llama-kv-cache.h
|
3e69319772
llama : update llama_decode_internal ref [no ci] (#11840)
|
hai 11 meses |
|
llama-mmap.cpp
|
90d987b105
mmap: add include for cerrno (#11296)
|
hai 1 ano |
|
llama-mmap.h
|
19b392d58d
llama-mmap: fix missing include (#11796)
|
hai 11 meses |
|
llama-model-loader.cpp
|
a5203b4465
llama : minor fixes for up llama load model speed (#11448)
|
hai 11 meses |
|
llama-model-loader.h
|
681149ced2
llama : add `llama_model_load_from_splits` (#11255)
|
hai 1 ano |
|
llama-model.cpp
|
bdcf8b6a56
cont : fix mmap flag print (#11699)
|
hai 11 meses |
|
llama-model.h
|
667d72846c
rpc : early register backend devices (#11262)
|
hai 1 ano |
|
llama-quant.cpp
|
681149ced2
llama : add `llama_model_load_from_splits` (#11255)
|
hai 1 ano |
|
llama-quant.h
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
hai 1 ano |
|
llama-sampling.cpp
|
27e8a23300
sampling: add Top-nσ sampler (#11223)
|
hai 11 meses |
|
llama-sampling.h
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
hai 1 ano |
|
llama-vocab.cpp
|
ffd0821c57
vocab : correctly identify LF token for GPT-2 style BPE tokenizer (#11496)
|
hai 11 meses |
|
llama-vocab.h
|
08f10f69c3
llama : remove notion of CLS token (#11064)
|
hai 1 ano |
|
llama.cpp
|
bdcf8b6a56
cont : fix mmap flag print (#11699)
|
hai 11 meses |
|
unicode-data.cpp
|
458367a906
server : better security control for public deployments (#9776)
|
hai 1 ano |
|
unicode-data.h
|
a39ab216aa
llama : reduce compile time and binary size (#9712)
|
hai 1 ano |
|
unicode.cpp
|
68ff663a04
repo : update links to new url (#11886)
|
hai 11 meses |
|
unicode.h
|
08ea539df2
unicode : improve naming style (#10838)
|
hai 1 ano |
Georgi Gerganov