QiuMike/VMsvga2ForQEMU
This is the VMware svga graphic card OSX driver for QEMU
Repositories
QiuMike/macos
MacOS inside a Docker container.
QiuMike/sglang
SGLang is a fast serving framework for large language models and vision language models.
QiuMike/lm-sys.github.io
The source of LMSYS website and blogs
QiuMike/Awesome-AgenticLLM-RL-Papers
QiuMike/TileRT
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
QiuMike/vllm-omni
A framework for efficient model inference with omni-modality models
QiuMike/one-api
LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.
QiuMike/anyrouter-check-in
支持 AnyRouter、AgentRouter 的多平台多账号签到，理论兼容所有基于 NewAPI、OneAPI 的平台。
QiuMike/claude-code
An independent Python feature port of Claude Code, entirely rewritting from scratch using oh-my-codex. Educational Purpose only.
QiuMike/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
QiuMike/TradingAgents
TradingAgents: Multi-Agents LLM Financial Trading Framework
QiuMike/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
QiuMike/vllm-ascend
Community maintained hardware plugin for vLLM on Ascend
QiuMike/SimAI
QiuMike/H2O
[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
QiuMike/SnapKV
QiuMike/gdrcopy
A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology
QiuMike/ReaLHF
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
QiuMike/KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
QiuMike/open-gpu-doc
Documentation of NVIDIA chip/hardware interfaces
QiuMike/openr
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
QiuMike/LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
QiuMike/TGS
Artifacts for our NSDI'23 paper TGS
QiuMike/CRAC-early-development
QiuMike/cuda-checkpoint
CUDA checkpoint and restore utility
QiuMike/flash-llm
Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
QiuMike/kvikio
KvikIO - High Performance File IO
QiuMike/DataLoaders_DALI
PyTorch DataLoaders implemented with DALI for accelerating image preprocessing
QiuMike/DALI
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.