Advancing 1.58-bit Quantization | Specialized in Tensor-Level Ternary Packing (TQ1_0) | Optimizing LLM Inference for the Atlas Scenario.
Popular repositories Loading
-
ATLAS-TQ1_0
ATLAS-TQ1_0 PublicTQ1.0 ternary inference engine for BitNet b1.58 on CPU. Pack + run Falcon3-1B/3B/7B/10B, no GPU needed.
Python 4
-
atlas-nomad-research
atlas-nomad-research PublicATLAS NOMAD-1 Research: 16x Bit-Packing, GGUF TQ1_0, VRAM Optimization for Edge AI
-
BitNet
BitNet PublicForked from microsoft/BitNet
Fork of microsoft/BitNet with ATLAS Ternary Packer - PR #548 pending
Python
-
-
-
opencode-tools
opencode-tools PublicBlazing fast, zero-dependency repository analysis and refactoring toolchain for AI-assisted workflows
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.