olivame a2cd34dd51 1. einsum('b i d, b j d -> b i j') → torch.bmm(q, k.transpose(-1,-2)) — 直接映射 rocBLAS batched GEMM ...

2. baddbmm 把 scale 融合进 GEMM，少一次 kernel launch
3. 第二个 einsum 同理换torch.bm
每一轮加速1到两秒

2026-02-08 18:54:48 +00:00

..

evaluation

1. einsum('b i d, b j d -> b i j') → torch.bmm(q, k.transpose(-1,-2)) — 直接映射 rocBLAS batched GEMM

2026-02-08 18:54:48 +00:00

run_base_model_inference.sh

init commit

2025-09-12 21:53:41 +08:00

run_real_eval_server.sh

upload real-robot deployment code

2025-09-23 15:13:22 +08:00

run_world_model_interaction.sh

init commit

2025-09-12 21:53:41 +08:00

train.sh

init commit

2025-09-12 21:53:41 +08:00

trainer.py

init commit

2025-09-12 21:53:41 +08:00