Georgi Gerganov
VERIFIED TECHNICAL DOSSIERSources checked

Georgi Gerganov

ggml.ai

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Georgi Gerganov. Every entry undergoes editorial source verification.

#1
IMPLEMENTATION Checked Sep 21, 2026

whisper.cpp: High-Performance Automatic Speech Recognition in Pure C/C++

Developed a pure C/C++ port of OpenAI Whisper speech recognition with zero external dependencies, streaming audio support, WebAssembly compilation, and hardware acceleration on Apple Silicon and mobile devices.

Model & Execution Context:OpenAI Whisper tiny/base/small/medium/large models, 16-bit float and 4-bit/5-bit/8-bit integer quantization.
Scope & Limitations

Real-time streaming requires audio buffering and speech activity detection (VAD) to prevent hallucinated audio loops.

#2
IMPLEMENTATION Checked Sep 21, 2026

llama.cpp: High-Performance C/C++ Foundation Model Inference Engine

Engineered a zero-dependency C/C++ LLM inference framework implementing 2-bit through 8-bit integer quantization (GGUF), ARM NEON, Apple Silicon Metal, CUDA, and AVX2 vector intrinsics, powering the modern local AI ecosystem.

Model & Execution Context:GGUF quantization format, Llama 2/3, Mistral, Qwen, DeepSeek; pure C/C++ runtime.
Scope & Limitations

Extreme low-bit quantizations (2-bit/3-bit) exhibit perplexity degradation on complex symbolic reasoning tasks.