Stars
Self-hosted native-Rust runtime for real-time voice agents. Own the stack: one binary in your own VPC or air-gapped, no hosted control plane. pipecat-compatible pipeline, in-process SIP/RTP, single…
GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, deployed and benchmarked. Generates in 16 GB of RAM.
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
⚡ Co-optimized LLM compression, static/dynamic runtime acceleration, and agent harness tuning for memory-constrained on-device agents.
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python depend…
The local UI to run and train text and diffusion models, including Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.
Gemma open-weight LLM library, from Google DeepMind
Generator Bootcamp Material: Learn Chisel the Right Way
A template project for beginning new Chisel work
llama.cpp fork with additional SOTA quants and improved performance
SGLang is a high-performance serving framework for large language models and multimodal models.
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
An end-to-end agent project for GPU kernel implementation, analysis, profiling, and iterative optimization. It helps an agent turn PyTorch logic or an existing kernel into a high-performance GPU ke…
Contract-Aware RTL Code Generation Agents with Temporal Tracing, Slicing and Formal Verification
ARM64 ELF Virtual Machine Protection System
中国专利.skill：从项目文档到交底书编写（挖点·查新·脱敏成文）+ 专利通俗解读（叙事·图谱·Obsidian 私库）。
FSA: Fusing FlashAttention within a Single Systolic Array
A paper list of spiking neural networks, including papers, codes, and related websites. 本仓库收集脉冲神经网络相关的顶会顶刊以及CNS论文和代码，正在持续更新中。
Backward compatible ML compute opset inspired by HLO/MHLO
The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.
An open-source, JEDEC JESD270-4A-compliant HBM4 memory subsystem (controller + PHY-shim + DFT + RAS + security wrapper) tightly coupled to an open RISC-V-native LPU accelerator. Apache-2.0 RTL, CER…
Framework providing operating system abstractions and a range of shared networking and memory services for common modern heterogeneous platforms.
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
A custom C++ routine to identify logic gates in the layout extracted netlist (SPICE) of digital circuits and generate gate-level Verilog netlist, in the presence of logic gate defintions from the s…