← Developers
Open on GitHub 
#57
Georgi Gerganov
@ggerganov · Bulgaria
89.0k
Weighted score
9.96k
Contributions
15
Repos
Top repos
- ggml-org/llama.cpp
- spiritbuun/buun-llama-cpp
- PrismML-Eng/llama.cpp
- ggml-org/whisper.cpp
- ggml-org/ggml
- ikawrakow/ik_llama.cpp
- Tiiny-AI/PowerInfer
- RWKV/rwkv.cpp
- ggml-org/llama.vim
- antimatter15/alpaca.cpp
Ranked AI repos11
12130
ggml-org/llama.cpp
+106
LLM inference in C/C++
130.4k· C++· Infrastructure
45620
ggml-org/whisper.cpp
+22
Port of OpenAI's Whisper model in C/C++
54.1k· C++· Infrastructure
3267784
ggml-org/ggml
+1
Tensor library for machine learning
15.4k· C++· Infrastructure
5586312
antimatter15/alpaca.cpp
+0
Locally run an Instruction-Tuned Chat-Style LLM
10.1k· C· Applications
19383974
Tiiny-AI/PowerInfer
+3
High-speed Large Language Model Serving for Local Deployment
9.82k· C++· Infrastructure
25671335
ikawrakow/ik_llama.cpp
+2
llama.cpp fork with additional SOTA quants and improved performance
3.28k· C++· Infrastructure
73543174
ggml-org/llama.vim
+0
Vim plugin for LLM-assisted code/text completion
2.18k· Vim Script· AI Engineering
27626468
RWKV/rwkv.cpp
+2
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
1.58k· C++· Infrastructure
27706630
ggml-org/llama.vscode
+2
VS Code extension for LLM-assisted code/text completion
1.53k· TypeScript· Applications
109977846
spiritbuun/buun-llama-cpp
+0
Experimental llama.cpp fork for inference research and development
883· C++· Infrastructure
954649
PrismML-Eng/llama.cpp
+10
LLM inference in C/C++
872· C++· Infrastructure