optimus-prime-source

Here are 3 public repositories matching this topic...

RNGD MoE expert offloading (hot experts on NPU HBM, cold experts on host CPU)

moe npu ai-rm ai-rm-l2 optimus-prime-source

PD-disaggregated serving across Furiosa RNGD (prefill) and Rebellions ATOM (decode) as llm-d pods

npu llm-serving pd-disaggregation ai-rm optimus-prime-source ai-rm-l3

Completion-fenced same-host heterogeneous NPU KV transport (RNGD -> ATOM), llm-d stage integration

p2p npu kv-cache ai-rm ai-rm-l2 optimus-prime-source

To associate your repository with the optimus-prime-source topic, visit your repo's landing page and select "manage topics."