Revert "[SYCL] fallback mmvq (#9088)" (#9579)

This reverts commit 50addec9a532a6518146ab837a85504850627316.

diff --git a/ggml/src/ggml-sycl.cpp b/ggml/src/ggml-sycl.cpp
index 16e6be4a0a12b73a155120ed8a69866ab38b0ed5..6978a31924d5fd37fa9d5419381fd1992de7ce0f 100644 (file)
--- a/ggml/src/ggml-sycl.cpp
+++ b/ggml/src/ggml-sycl.cpp
@@ -3496,8 +3496,7 @@ static void ggml_sycl_mul_mat(ggml_backend_sycl_context & ctx, const ggml_tensor
 
     bool use_mul_mat_vec_q =  ggml_is_quantized(src0->type)
         && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
-        && src1->ne[1] <= MMVQ_MAX_BATCH_SIZE
-        && (ctx.stream()->get_backend() == sycl::backend::ext_oneapi_cuda || src1->ne[1] > MMVQ_MIN_BATCH_SIZE);
+        && src1->ne[1] <= MMVQ_MAX_BATCH_SIZE;
 
     bool use_mul_mat_q =  ggml_sycl_supports_mmq(src0->type)
         && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32;

diff --git a/ggml/src/ggml-sycl/common.hpp b/ggml/src/ggml-sycl/common.hpp
index 05947ccb746f26d6ab8f51962e4e8871e3da0efc..bc0faa867dcfe02f8f9f1dacee7ba4c965d5c109 100644 (file)
--- a/ggml/src/ggml-sycl/common.hpp
+++ b/ggml/src/ggml-sycl/common.hpp
@@ -134,7 +134,6 @@ typedef sycl::float2 dfloat2;
 #endif // GGML_SYCL_F16
 
 #define MMVQ_MAX_BATCH_SIZE  8
-#define MMVQ_MIN_BATCH_SIZE  4
 
 static const int8_t kvalues_iq4nl[16]={-127, -104, -83, -65, -49, -35, -22, -10, 1, 13, 25, 38, 53, 69, 89, 113};