Xuan Son Nguyen 4d2b3d8804

lora : improve compat with mergekit-extract-lora (#11131) ...

* (wip) support mergekit-extracted lora

* support mergekit-extract-lora

* use lora->get_scale

* correct comment

* correct norm name & condition

* add some hints

2025-01-08 15:59:53 +01:00

..

CMakeLists.txt

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-adapter.cpp

lora : improve compat with mergekit-extract-lora (#11131)

2025-01-08 15:59:53 +01:00

llama-adapter.h

lora : improve compat with mergekit-extract-lora (#11131)

2025-01-08 15:59:53 +01:00

llama-arch.cpp

llama : Add support for DeepSeek V3 (#11049)

2025-01-04 21:06:11 +01:00

llama-arch.h

llama : Add support for DeepSeek V3 (#11049)

2025-01-04 21:06:11 +01:00

llama-batch.cpp

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-batch.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-chat.cpp

llama : Add support for DeepSeek V3 (#11049)

2025-01-04 21:06:11 +01:00

llama-chat.h

llama : Add support for DeepSeek V3 (#11049)

2025-01-04 21:06:11 +01:00

llama-context.cpp

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-context.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-cparams.cpp

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-cparams.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-grammar.cpp

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-grammar.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-hparams.cpp

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-hparams.h

llama : Add support for DeepSeek V3 (#11049)

2025-01-04 21:06:11 +01:00

llama-impl.cpp

GGUF: C++ refactor, backend support, misc fixes (#11030)

2025-01-07 18:01:58 +01:00

llama-impl.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-kv-cache.cpp

llama : rename missed batch params/vars to ubatch (#10059)

2025-01-06 11:28:17 +02:00

llama-kv-cache.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-mmap.cpp

mmap : fix fileno macro clash (#11076)

2025-01-06 10:52:38 +02:00

llama-mmap.h

mmap : fix fileno macro clash (#11076)

2025-01-06 10:52:38 +02:00

llama-model-loader.cpp

GGUF: C++ refactor, backend support, misc fixes (#11030)

2025-01-07 18:01:58 +01:00

llama-model-loader.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-model.cpp

llama : update llama_model API names (#11063)

2025-01-06 10:55:18 +02:00

llama-model.h

llama : Add support for DeepSeek V3 (#11049)

2025-01-04 21:06:11 +01:00

llama-quant.cpp

llama : avoid hardcoded QK_K (#11061)

2025-01-08 16:19:36 +02:00

llama-quant.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-sampling.cpp

llama : use LLAMA_TOKEN_NULL (#11062)

2025-01-06 10:52:15 +02:00

llama-sampling.h

llama : add DRY sampler (#9702)

2024-10-25 19:07:34 +03:00

llama-vocab.cpp

llama : use LLAMA_TOKEN_NULL (#11062)

2025-01-06 10:52:15 +02:00

llama-vocab.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama.cpp

lora : improve compat with mergekit-extract-lora (#11131)

2025-01-08 15:59:53 +01:00

unicode-data.cpp

server : better security control for public deployments (#9776)

2024-10-08 13:27:04 +02:00

unicode-data.h

llama : reduce compile time and binary size (#9712)

2024-10-02 15:49:55 +02:00

unicode.cpp

llama : Add support for DeepSeek V3 (#11049)

2025-01-04 21:06:11 +01:00

unicode.h

unicode : improve naming style (#10838)

2024-12-16 12:31:45 +02:00