#moe

avifenesh/bw24

Rust

89

health

From-scratch Rust+CUDA inference engine, bit-exact by construction — NVFP4, MoE, MTP speculative decoding, tuned against measured limits of one RTX 5090 Laptop (sm_120a).

czy0729/Bangumi

TypeScript

88

health

:electron: An unofficial https://bgm.tv ui first app client for Android and iOS, built with React Native. 一个无广告、以爱好为驱动、不以盈利为目的、专门做 ACG 的类似豆瓣的追番记录，bgm.tv 第三方客户端。为移动端重新设计，内置大量加强的网页端难以实现的功能，且提供了相当的自定义选项。 目前已适配 iOS / Android。

modelscope/ms-swift

Python

88

health

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

openinfer-project/openinfer

Rust

84

health

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2