Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703)
* CUDA multi GPU + scratch ggml_cuda_compute_forward Tensor parallelism ggml_cuda_add ggml_cuda_rms_norm ggml_cuda_silu CUDA scratch buffer --main-gpu CLI option
J
Johannes Gäßler committed
17366df842e358768c0df7024484fffecfc7865b
Parent: 44f906e
Committed by GitHub <noreply@github.com>
on 6/6/2023, 7:33:23 PM