gitpulse

mw00/project-maya

Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.

2,946 stars407 forksC++MITpushed 2026-11-16

View on GitHub →

Star momentum

Today+33 (+1.1%)
This week+223 (+8.2%)
This month—

Topics

cudaglmglm-5llmllm-inferencelocal-llmmixture-of-expertsmoeopenai-apiquantizationrocmself-hosteddeepseekdeepseek-v4minimaxminimax-m3anthropic-apiggufofflinewindows