OSS Radar
mw00/project-maya
Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server… Why it matters: useful plumbing for shipping LLM-powered features.
GitHub description: Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
Stars
746
Last 24h
+105est.
Last 7 days
+737est.
Forks
87
Star history
GitHub stars over time. A steeper line means the repo is gaining attention faster.
Not enough history yet. OSS Radar records stars every hour, so this chart fills in over the next few hours.
* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.
Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/mw00/project-maya)<a href="https://ossradar.net/repo/mw00/project-maya"><img src="https://ossradar.net/badge/mw00/project-maya" alt="Trending on OSS Radar"></a>About project-maya
mw00/project-maya is a C++ project in the LLM tooling category, created 7 days ago. It has 746 GitHub stars and 87 forks, and gained +737 stars over the last 7 days (early estimate), ranking #1 of 162 LLM tooling repos tracked by OSS Radar this week.
See more trending LLM tooling repos or the top AI repos this week.
- Language
- C++
- Category
- LLM tooling
- Created
- Oct 6, 2026
- Last code push
- today (Oct 13, 2026)
- Latest release
- v1.1.7 today
- cuda
- glm
- glm-5
- llm
- llm-inference
- local-llm
- mixture-of-experts
- moe
- openai-api
- quantization
- rocm
- self-hosted
Similar rising repos
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU. Why it matters: useful plumbing for shipping LLM-powered features.
- sgl-project/sglang+7est.
SGLang is a high-performance serving framework for large language models and multimodal models. Why it matters: useful plumbing for shipping LLM-powered features.
- syv-ai/HyperQwen+7est.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer… Why it matters: useful plumbing for shipping LLM-powered features.
- bojieli/ai-infra-book+28est.
《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验. Why it matters: useful plumbing for shipping LLM-powered features.
Your Cheat Sheet for AI Engineering Interview – Questions and Answers. Why it matters: useful plumbing for shipping LLM-powered features.
- vllm-project/vllm+7est.
A high-throughput and memory-efficient inference and serving engine for LLMs. Why it matters: useful plumbing for shipping LLM-powered features.