@@ -42,8 +42,6 @@ <h3>GGML - AI at the edge</h3>
42
42
< li > Low-level cross-platform implementation</ li >
43
43
< li > Integer quantization support</ li >
44
44
< li > Broad hardware support</ li >
45
- < li > Automatic differentiation</ li >
46
- < li > ADAM and L-BFGS optimizers</ li >
47
45
< li > No third-party dependencies</ li >
48
46
< li > Zero memory allocations during runtime</ li >
49
47
</ ul >
@@ -69,43 +67,9 @@ <h4>The <a href="https://github.com/ggerganov/ggml"><b>ggml</b></a> way</h4>
69
67
</ li >
70
68
</ ul >
71
69
72
- < h4 > Projects</ h4 >
73
-
74
- < ul >
75
- < li >
76
- < a href ="https://github.com/ggerganov/whisper.cpp "> whisper.cpp</ a >
77
-
78
- < p > High-performance inference of OpenAI's Whisper automatic speech recognition model</ p >
79
-
80
- < p > The project provides a high-quality speech-to-text solution that runs on Mac, Windows, Linux,
81
- iOS, Android, Raspberry Pi, and Web</ p >
82
- </ li >
83
- < li >
84
- < a href ="https://github.com/ggerganov/llama.cpp "> llama.cpp</ a >
85
-
86
- < p > Inference of Meta's LLaMA model (and others) in pure C/C++</ p >
87
-
88
- < p > The project provides efficient inference across a wide range of hardware and serves as the
89
- foundation for numerous LLM-based applications</ p >
90
- </ li >
91
- </ ul >
92
-
93
70
< h4 > Contributing</ h4 >
94
71
95
- < ul >
96
- < li >
97
- < p > The best way to support the project is by contributing to the codebase< p >
98
- </ li >
99
- < li >
100
- < p > If you wish to financially support the project, please consider becoming a sponsor to any of the
101
- contributors that are already involved:</ p >
102
- < ul >
103
- < li > < a href ="https://github.com/ggerganov/llama.cpp/graphs/contributors "> llama.cpp contributors</ a > </ li >
104
- < li > < a href ="https://github.com/ggerganov/whisper.cpp/graphs/contributors "> whisper.cpp contributors</ a > </ li >
105
- < li > < a href ="https://github.com/ggerganov/ggml/graphs/contributors "> ggml contributors</ a > </ li >
106
- </ ul >
107
- </ li >
108
- </ ul >
72
+ < p > Join the development at < a href ="https://github.com/ggml-org "> ggml-org</ a > on GitHub.
109
73
110
74
< h4 > Company</ h4 >
111
75
0 commit comments