From 342c923c88ca25764e35982f65f2ddb8f90c3cdd Mon Sep 17 00:00:00 2001 From: shifulegend Date: Sat, 4 Jul 2026 05:20:55 +0000 Subject: [PATCH] Add Project Zero to CPU/NPU/FPGA/Mobile Inference --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 2845f6b..3b8d538 100644 --- a/README.md +++ b/README.md @@ -507,6 +507,7 @@ python3 download_pdfs.py # The code is generated by Doubao AI |2025.12|🔥[**Grail-V/PSE**] Non-bijunctive Attention Collapse via POWER8 vec_perm — 8.8x CPU Inference Speedup(@Elyan Labs)|[[zenodo]](https://doi.org/10.5281/zenodo.14862410)|[[ram-coffers]](https://github.com/Scottcjn/ram-coffers) ![](https://img.shields.io/github/stars/Scottcjn/ram-coffers.svg?style=social)|⭐️ | |2025.12|🔥[**llama-cpp-power8**] POWER8 optimizations for llama.cpp: vec_perm non-bijunctive collapse, IBM MASS integration, dcbt resident prefetch. 8.8x speedup over stock(@Scottcjn)|[[github]](https://github.com/Scottcjn/llama-cpp-power8)|[[llama-cpp-power8]](https://github.com/Scottcjn/llama-cpp-power8) ![](https://img.shields.io/github/stars/Scottcjn/llama-cpp-power8.svg?style=social)|⭐️ | |2025.12|🔥[**RAM Coffers**] NUMA-aware weight banking for LLM inference. Maps brain hemisphere cognitive functions to NUMA topology for intelligent routing and selective prefetch(@Scottcjn)|[[github]](https://github.com/Scottcjn/ram-coffers)|[[ram-coffers]](https://github.com/Scottcjn/ram-coffers) ![](https://img.shields.io/github/stars/Scottcjn/ram-coffers.svg?style=social)|⭐️ | +|2026.06|[**Project Zero**] Zero-dependency C99 engine running BitNet ternary and GGUF dense in one binary; LUT-based ternary kernel hits 36 tok/s on Xeon (1.83x bitnet.cpp), no Python/BLAS(@shifulegend)|[[github]](https://github.com/shifulegend/project-zero)|[[project-zero]](https://github.com/shifulegend/project-zero) ![](https://img.shields.io/github/stars/shifulegend/project-zero.svg?style=social)|⭐️ | ### 📖Non Transformer Architecture ([©️back👆🏻](#paperlist))