GitHub · Sass

kacper-daftcode/vLLM-Moet

Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and 2-bit experts on vLLM v0.24.0

Stars
579
Forks
49
Stars gained in 24 hours
0
Forks gained in 24 hours
0

Topics: blackwell, cuda, deepseek, llm-inference, moe, rtx-5090, rtx-pro-6000, sass, sm120, vllm

Latest data point: Nov 21, 2026 · 579 stars · 49 forks

Open on GitHub