融合Android原生质感与二次元美学：Material Design 3规范下的Astro博客主题（Tailwind CSS实现）

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM training.

Nano vLLM

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Awesome Low-Rank Adaptation

A unified inference and post-training framework for accelerated video generation.

收集户晨风的所有内容

⭐ A simple, fast and powerful blog & document theme built by Astro

Export and Share your ChatGPT conversation history

RISC-V Open Source Supervisor Binary Interface

[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

TraceRL & TraDo-8B: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

同文安卓輸入法平臺3.x/Android-rime/Rime Input Method Engine for Android

【小狼毫】Rime for Windows

This will run the new self-hosted github actions runners with docker-in-docker

Writing an OS in 1,000 lines.

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Litex is a simple formal language Learnable in 2 hours, not 1 year. It scales formal reasoning in AI era.

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

一键导出PC微信聊天记录工具

chat log tool, easily use your own chat data. 聊天记录工具，轻松使用自己的聊天数据

[NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning