CodingPlatelets
Follow
Lists (1)
Starred repositories
Deploy mihomo proxy kernel + Metacubexd web UI on a Linux server
A multi-platform proxy client based on ClashMeta,simple and easy to use, open-source and ad-free.
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
A framework for efficient model inference with omni-modality models
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Information collection for the Happy Horse AI video generator model. Official demo and updates at happyhorses.io.
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
FlashInfer: Kernel Library for LLM Serving
Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions
华中科技大学 计算机学院 硕士/博士 毕业论文 Latex 模板（2025修改）
An extremely fast Python linter and code formatter, written in Rust.
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
ZJU-Connect 图形界面 - 支持 aTrust 和 EasyConnect 协议
Nano vLLM with vLLM v1's request scheduling strategy and chunked prefill
Nano vLLM with vLLM v1's request scheduling strategy and chunked prefill
An extremely fast Python package and project manager, written in Rust.
自动更新 hosts 文件的 IP 地址，缓解中国大陆访问 GitHub 及其相关服务时遇到的网络问题
Tool for generating Clang's JSON Compilation Database files for make-based build systems.
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, GLM and other models.
Tile primitives for speedy kernels
