Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

nlp kosmos deepnet multimodal bitnet pre-trained-model unilm minilm layoutlm beit document-ai layoutxlm trocr foundation-models llm beit-3 xlm-e mllm kosmos-1 textdiffuser

• Updated Sep 21, 2026
• Python

Official implementation for BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation (CoRL 2026, Spotlight)

robotics 1-bit bitnet multimodal-large-language-models bitnet-llm bitvla

• Updated Nov 9, 2026
• Python

Kindi 0.5: local LLM inference on low-cost NVIDIA GPUs (Kepler to the RTX 50 series and the CMP 170HX), AMD Radeon 780M, 840M and 8060S, and CPUs. Bonsai 2B-27B, AH-Nanbeige4.3-33B and experimental Nemotron, with an OpenAI-compatible server.

pascal amd cuda kepler ternary ampere rocm maxwell quadro bitnet tensor-parallelism local-llm llm-inference openai-compatible low-cost-gpu

• Updated Nov 10, 2026
• Python

A ternary, zero-heap tiny language model that runs inside a $2 microcontroller — bit-exact Python <-> C99 <-> Cortex-M3 (QEMU) parity. Apache-2.0.

machine-learning microcontroller embedded cortex-m esp32 stm32 qemu quantization language-model ternary bitnet edge-ai on-device-ai tinyml llm small-language-model

• Updated Jul 8, 2026
• Python

Running Microsoft's BitNet via Electron, React & Astro

electron benchmarking ai reactjs 1-bit bitnet perplexity inference-framework astrojs large-language-models llm 1-bit-quantization

• Updated Sep 26, 2025
• JavaScript

CPU-optimized LLM inference engine (C)

cpu c99 inference simd moe avx512 ternary bitnet zero-dependencies cpu-inference llm gguf deepseek

• Updated Nov 11, 2026
• C

BitNet-Stack - Run a small BitNet model on local machine with one Docker command, and chat in browser.

microsoft docker open-source query ai ml bitnet huggingface llm 1bit-llm bitnet-stack

• Updated Apr 19, 2026
• HTML

Implementing the BitNet model in Rust

rust candle bitnet llm

• Updated Apr 18, 2024
• Rust

Running Microsoft's BitNet inference framework via FastAPI, Uvicorn and Docker.

python docker benchmarking inference 1-bit bitnet perplexity uvicorn fastapi multi-chat server-orchestration llm model-context-protocol

• Updated Jul 2, 2025
• Python

pure pytorch implementation of Microsoft's BitNet b1.58 2B4T

bitnet llm

• Updated Mar 26, 2026
• Python

Foundational ternary-model inference & training library — CUDA + CPU, BitNet/TQ ternary kernels

rust machine-learning cuda quantization ternary inference-engine bitnet llm llm-inference gguf

• Updated Nov 9, 2026
• Rust

All the important tools for BITNET/HNET programs like relay chat, xyzzy, YWAKEUP, IUCVTRAP, CLRSCRN

chat bitnet nje hnet

• Updated Feb 20, 2026
• Pascal

Official implementation of BitMamba-2. A scalable 1.58-bit State Space Model (Mamba-2 + BitNet) trained from scratch on 150B tokens. Includes JAX training code and high-performance C++ inference engine.

cpp flax quantization ssm mamba efficient-inference tpu jax bitnet llm 1-58-bit

• Updated Feb 4, 2026
• Python

Run BitNet b1.58 ternary LLMs with WebGPU — in browsers and native apps

typescript inference ternary webgpu bitnet wgsl llm

• Updated Nov 5, 2026
• TypeScript

Ultra-lightweight C++ inference engine for BitMamba-2 (1.58-bit SSM). Runs 1B models on consumer CPUs at 50+ tok/s using <700MB RAM. No heavy dependencies.

cpp inference simd quantization ssm mamba edge-computing low-resource bitnet embedded-ai

• Updated Jun 2, 2026
• Python

Software side of an LLM running inside a DRAM chip via charge-sharing PIM (BitNet b1.58 on DRAM-Bender silicon).

safari pim dram bitnet in-memory-computing llm charge-sharing dram-bender

• Updated Aug 17, 2026
• C++

Portable C inference engine for BitMamba-2 models

inference-engine bitnet

• Updated Jun 22, 2026
• C

BitNet: Learning-Based-Bit-Depth-Expansion

bde bitnet bit-depth bit-depth-expansion learning-based-bit-depth-expansion

• Updated Feb 9, 2025
• Python

Single-launch batch-1 decode engine for PrismML Bonsai 27B (ternary and 1-bit) on NVIDIA GPUs. 1.76x the vendor llama.cpp fork on H100, same outputs.

gpu cuda nvidia quantization bitnet llama-cpp llm-inference megakernel

• Updated Jul 16, 2026
• Cuda

Rust bindings for bitnet.cpp based on llama-cpp-4

rust machine-learning llama bitnet ggml

• Updated Dec 28, 2025
• Rust