| .. |
|
CMakeLists.txt
|
15f5d96037
build : fix build info generation and cleanup Makefile (#3920)
|
2 年之前 |
|
base64.hpp
|
381efbf480
llava : expose as a shared library for downstream projects (#3613)
|
2 年之前 |
|
build-info.cpp.in
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
2 年之前 |
|
common.cpp
|
9fb13f9584
common : add `--version` option to show build info in CLI (#4433)
|
2 年之前 |
|
common.h
|
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
|
2 年之前 |
|
console.cpp
|
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184)
|
2 年之前 |
|
console.h
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 年之前 |
|
grammar-parser.cpp
|
4fa44e84ad
grammar-parser : fix typo (#4318)
|
2 年之前 |
|
grammar-parser.h
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 年之前 |
|
log.h
|
9494d7c477
english : use `typos` to fix comments and logs (#4354)
|
2 年之前 |
|
sampling.cpp
|
caa9249217
common : fix compile warning
|
2 年之前 |
|
sampling.h
|
52c8bc3cf3
sampling : custom samplers order (#4285)
|
2 年之前 |
|
stb_image.h
|
370359e5ba
examples: support LLaVA v1.5 (multimodal model) (#3436)
|
2 年之前 |
|
train.cpp
|
ba4cf5c0bf
train : move number of gpu layers argument parsing to common/train.cpp (#4074)
|
2 年之前 |
|
train.h
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
2 年之前 |
Siwen Yu
9fb13f9584
common : add `--version` option to show build info in CLI (#4433)