SYCL: Add gated linear attention kernel (llama/11175)

* SYCL: Add Gated Linear attention kernel

* glahpp: add a space at the end of file

* gla: Put the barrier inside the main logic loop
This commit is contained in:
Akarshan Biswas
2025-01-15 08:50:17 +05:30
committed by Georgi Gerganov
parent 8e0143e205
commit 9700cfb0a3
4 changed files with 118 additions and 0 deletions

View File

@ -4040,6 +4040,9 @@ bool ggml_sycl_compute_forward(ggml_backend_sycl_context & ctx, struct ggml_tens
case GGML_OP_RWKV_WKV6:
ggml_sycl_op_rwkv_wkv6(ctx, dst);
break;
case GGML_OP_GATED_LINEAR_ATTN:
ggml_sycl_op_gated_linear_attn(ctx, dst);
break;
default:
return false;
}
@ -4507,6 +4510,7 @@ static bool ggml_backend_sycl_device_supports_op(ggml_backend_dev_t dev, const g
case GGML_OP_LEAKY_RELU:
case GGML_OP_TIMESTEP_EMBEDDING:
case GGML_OP_RWKV_WKV6:
case GGML_OP_GATED_LINEAR_ATTN:
return true;
default:
return false;