• 1
• 0
• 0

jiangyunxing/llama.cpp-mtp

About Fused TBQ4 Flash Attention + MTP + Shared Tensors for llama.cpp — 82+ tok/s with lossless 4.25 bpv KV cache at 200K context on RTX 4090

• 1
• 0
• 0

jiangyunxing/llama.cpp

LLM inference in C/C++

• 1
• 0
• 0

jiangyunxing/fastllm

fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

• 1
• 0
• 0

jiangyunxing/GLM

GLM (General Language Model)

• 1
• 0
• 0

jiangyunxing/graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

• 1
• 0
• 0

jiangyunxing/sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

• 1
• 0
• 0

jiangyunxing/opencode

The open source coding agent.

• 1
• 0
• 0

jiangyunxing/claude-code-templates

CLI tool for configuring and monitoring Claude Code

• 1
• 0
• 0

jiangyunxing/marker

Convert PDF to markdown + JSON quickly with high accuracy

• 1
• 0
• 0

jiangyunxing/warp

Warp is an agentic development environment, born out of the terminal.

• 2
• 1
• 0

jiangyunxing/hermes-webui

Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!

• 1
• 0
• 0

jiangyunxing/hermes-agent

The agent that grows with you

• 1
• 0
• 0

jiangyunxing/mindzj

• 1
• 0
• 1

jiangyunxing/openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

• 1
• 0
• 0

jiangyunxing/CMake

Mirror of CMake upstream repository

• 1
• 0
• 0

jiangyunxing/Pillow

Python Imaging Library (fork)

• 1
• 1
• 0

jiangyunxing/FinceptTerminal

FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making i

• 1
• 0
• 0

jiangyunxing/calculus_made_easy

Chinese translation of Calculus Made Easy

• 1
• 0
• 0

jiangyunxing/scipy

SciPy library main repository

• 1
• 0
• 0

jiangyunxing/old-code