Popular repositories Loading

1. zerfoo zerfoo Public

   Production-grade ML inference and training framework in pure Go. 234 tok/s on Gemma 3 1B — 18.8% faster than Ollama. Zero CGo, embeddable as a library, GGUF models, OpenAI-compatible API.

   Go 5 1

2. float16 float16 Public

   IEEE 754 half-precision (Float16) and BFloat16 arithmetic library for Go. Lossless round-trip conversion, configurable rounding modes, and full special-value support.

   Go 1 1

3. zmf zmf Public archive

   Zerfoo Model Format

   Makefile 1 1

4. zonnx zonnx Public

   ONNX-to-GGUF model converter CLI. Convert HuggingFace ONNX models to GGUF format for use with Zerfoo and llama.cpp. CGo-free, single static binary.

   Go 1 1

5. gemma3 gemma3 Public

   Go 1

6. float8 float8 Public

   FP8 (E4M3FN) arithmetic library for Go. Configurable precision/range trade-offs for quantized ML inference and memory-constrained applications.

   Go 1