slaren 0d56246f4b ggml : group all experts in a single ggml_mul_mat_id (#6505) ...

* ggml : group all experts in a single ggml_mul_mat_id
cuda : improve mmid row copy

* cuda : fix bin bcast with non-cont src0

* test-backend-ops : only run all mul mat tests for base types

* llama : disable moe offloading with SYCL

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

2024-04-18 15:18:48 +02:00

676 B

Executable File

Raw Blame History

View Raw