Ternary Weights Network for Darknet
-
Updated
Jun 10, 2020 - C
#
ternary-weights
Here are 4 public repositories matching this topic...
PERSPECTIVE v2 — A 1.05 trillion parameter sparse Mixture-of-Experts language model that runs on consumer hardware (4 GB VRAM + 32 GB RAM). Features O(1) perspective decay recurrence, 3D torus manifold routing, native ternary {-1,0,+1} weights, holographic distributed memory, and hard geometric safety constraints. Built in Rust.
nlp rust machine-learning research deep-learning neural-network transformer moe language-model ai-safety efficient-inference consumer-hardware mixture-of-experts on-device-ai ternary-weights llm sparse-models holographic-memory manifold-routing novel-architecture
-
Updated
Feb 20, 2026 - Rust
Interactive Training Dashboard & CAGS-Operator Verification for JamOne Nano.
machine-learning compression optimization neural-networks ternary-weights cpu-training llm ai-efficiency
-
Updated
Mar 20, 2026 - Python
Custom CUDA kernels for accelerating 1.58-bit ternary LLM inference with 2:4 structured sparsity on consumer Ampere GPUs. Exploits both ternary arithmetic (no multiplies) and hardware sparse tensor cores to maximize throughput on RTX 3060. Based on the Sparse-BitNet paper (Zhang et al., 2026).
sparsity gpu cuda transformer cpp17 cuda-kernels quantization ampere structured-sparsity bitnet ternary-weights cusparselt llm-inference
-
Updated
Mar 11, 2026 - Cuda
Improve this page
Add a description, image, and links to the ternary-weights topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the ternary-weights topic, visit your repo's landing page and select "manage topics."