Pinned Repositories
BentoDiffusion
OneDiffusion: Run any Stable Diffusion models and fine-tuned weights with ease
BentoML
Model Serving Made Easy
fakebox
toy dsp library in python
GenExprForVSCode
Max's GenExpr mode for VS Code, converted from https://github.com/emmanueljourdan/GenExprForSublime
hua
Hua (㕦) is a hy-like lisp language to lua compiler.
lighterllm
nanohat-oled-lite
lightweight script for nanopi oled hat
nord-lead-viewer
nord lead 2x patch viewer
retromoon
retro forth in lua
zsy.ds4
[zsy.ds4] is is a simple max patch to handle Dualshock 4 inputs (over bluetooth)
larme's Repositories
larme/BentoDiffusion
OneDiffusion: Run any Stable Diffusion models and fine-tuned weights with ease
larme/BentoML
Model Serving Made Easy
larme/BentoSVD
larme/dockerfiles
my dockerfiles
larme/lighterllm
larme/OpenLLM
An open platform for operating large language models (LLMs) in production. Fine-tune, serve, deploy, and monitor any LLMs with ease.
larme/outlines
Structured Text Generation
larme/zsy.common
my max package for common utils
larme/analysis_claude_code
本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档，以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。
larme/Awesome-ML-SYS-Tutorial
My learning notes/codes for ML SYS.
larme/bento-fastapi-example
larme/bento-trtllm
larme/BentoVLLMXTTS
larme/cl-portaudio
Common Lisp bindings to portaudio library
larme/claude-loop
larme/corne-zmk-config
zmk config for the corne keyboard
larme/cuda-mode-lectures
Material for gpu-mode lectures
larme/Faster_SGEMM_CUDA
FP32 matrix multiplication of large matrices in some cases much faster than cuBLAS.
larme/gen_ext
gen_ext is a wrapper that lets you compile code exported from a Max gen~ object into an "external" object that can be loaded into a PureData patch.
larme/genexpr-mode
A emacs mode for developing GenExpr
larme/keebart-zmk-config
larme/melpa
Recipes and build machinery for the biggest Emacs package repo
larme/mn12b
larme/penpen
larme/picoGPT
An unnecessarily tiny implementation of GPT-2 in NumPy.
larme/SDT
Sound Design Toolkit
larme/sglang
SGLang is a fast serving framework for large language models and vision language models.
larme/srcs2md
A CLI utility to generate markdown files from source code using glob patterns
larme/vial-cli-loader
restore vial layout to keyboard
larme/weir
A system for making generative systems