vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : group all experts in a single ggml_mul_mat_id (#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 GitHub
parent 03c0946d73
commit 0d56246f4b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 971 additions and 821 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);
}