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

This reverts commit 50addec.
ggerganov · Sep 23, 2024 · e62e978 · e62e978
1 parent c35e586
commit e62e978
Show file tree

Hide file tree

Showing 2 changed files with 1 addition and 3 deletions.
diff --git 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
@@ -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};