@typesafeai I rebuilt the idea in the open: OpenJev. Ran it on a GTX 1650. 4GB

@typesafeai I rebuilt the idea in the open: OpenJev. Ran it on a GTX 1650. 4GB VRAM. No A100. No datacenter. One shared state. One KV cache. One forward pass. Now the real test:

@typesafeai I rebuilt the idea in the open: OpenJev. Ran it on a GTX 1650. 4GB VRAM. No A100. No datacenter. One shared state. One KV cache. One forward pass. Now the real test: Jev vs OpenJev. Same weights. Same questions. Latency. tok/s. Calibration. https://t.co/yZooTDtiak