ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-12 20:18:08 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

ggml : group all experts in a single ggml_mul_mat_id (llama/6505)

Browse Source 
* 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>
This commit is contained in:
slaren
2024-04-18 15:18:48 +02:00
committed by Georgi Gerganov
parent c97796aa0f
commit c96b0a938e
8 changed files with 730 additions and 681 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml-sycl.cpp
View File

@ -17752,7 +17752,7 @@ GGML_CALL static bool ggml_backend_sycl_supports_op(ggml_backend_t backend, cons
GGML_CALL static bool ggml_backend_sycl_offload_op(ggml_backend_t backend, const ggml_tensor * op) {
const int min_batch_size = 32;
return op->ne[1] >= min_batch_size && op->op != GGML_OP_GET_ROWS;
return op->ne[1] >= min_batch_size && op->op != GGML_OP_GET_ROWS && op->op != GGML_OP_MUL_MAT_ID;
GGML_UNUSED(backend);
}