Misby's starred repositories

Language:JavaStargazers:9Issues:0Issues:0

llm_kvcache_sparsity

Implement some method of LLM KV Cache Sparsity

Language:PythonStargazers:12Issues:0Issues:0

agi

Android GPU Inspector

Language:GoLicense:Apache-2.0Stargazers:926Issues:0Issues:0

MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

Language:PythonLicense:Apache-2.0Stargazers:7999Issues:0Issues:0

gpt_academic

为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

Language:PythonLicense:GPL-3.0Stargazers:62246Issues:0Issues:0

llamafile

Distribute and run LLMs with a single file.

Language:C++License:NOASSERTIONStargazers:17147Issues:0Issues:0

aimet

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Language:PythonLicense:NOASSERTIONStargazers:2023Issues:0Issues:0

MCSD

Multi-Candidate Speculative Decoding

Language:PythonLicense:MITStargazers:21Issues:0Issues:0

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

License:BSD-3-ClauseStargazers:1Issues:0Issues:0

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Language:PythonLicense:BSD-3-ClauseStargazers:5374Issues:0Issues:0

FastGPT

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

Language:TypeScriptLicense:NOASSERTIONStargazers:15610Issues:0Issues:0

EAGLE

Official Implementation of EAGLE-1 and EAGLE-2

Language:PythonLicense:Apache-2.0Stargazers:669Issues:0Issues:0

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

Language:Jupyter NotebookLicense:MITStargazers:9725Issues:0Issues:0

llama2.c

Inference Llama 2 in one file of pure C

Language:CLicense:MITStargazers:16847Issues:0Issues:0

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Language:C++License:MITStargazers:7666Issues:0Issues:0

tvm_mlir_learn

compiler learning resources collect.

Language:PythonStargazers:1957Issues:0Issues:0
Stargazers:1Issues:0Issues:0
Language:HTMLStargazers:4Issues:0Issues:0

tflite-support

TFLite Support is a toolkit that helps users to develop ML and deploy TFLite models onto mobile / ioT devices.

Language:C++License:Apache-2.0Stargazers:364Issues:0Issues:0

MegEngine

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

Language:C++License:Apache-2.0Stargazers:4738Issues:0Issues:0

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Language:C++License:NOASSERTIONStargazers:19789Issues:0Issues:0

ArmNeonOptimization

Arm neon optimization practice

Language:C++License:MITStargazers:385Issues:0Issues:0

nuttx

Apache NuttX is a mature, real-time embedded operating system (RTOS)

Language:CLicense:Apache-2.0Stargazers:2507Issues:0Issues:0

coder-kung-fu

开发内功修炼

Language:CLicense:Apache-2.0Stargazers:6027Issues:0Issues:0

tiny-training

On-Device Training Under 256KB Memory [NeurIPS'22]

License:MITStargazers:1Issues:0Issues:0

models

Models and examples built with TensorFlow

License:Apache-2.0Stargazers:2Issues:0Issues:0

gr-ieee802-11

IEEE 802.11 a/g/p Transceiver

Stargazers:2Issues:0Issues:0

rogsoft

software center for hnd/axhnd/axhnd.675x routers

Stargazers:2Issues:0Issues:0

ceres-script

Python script to build ceres on Windows platform

Stargazers:1Issues:0Issues:0