Revert "set flags to optimize for mmq"

This reverts commit 8ad0d29ef8.
2026-09-19 09:15:18 +02:00 · 2024-06-26 14:32:58 +08:00
parent a7a4e238fb
commit 7959e937a1
1 changed files with 0 additions and 1 deletions
@@ -8,7 +8,6 @@
 #include <cstdint>

 #define MMQ_DP4A_MAX_BATCH_SIZE 64 // Max. batch size to use for dp4a MMQ kernels when FP16 tensor cores are available.
-#define GGML_CUDA_FORCE_MMQ

 typedef void (*load_tiles_mmq_t)(const char * __restrict__ x, int * x_tile, const int & kbx0, const int & i_max, const int & stride);
 typedef void (*vec_dot_mmq_t)(const int * __restrict__ x, const int * __restrict__ y, float * __restrict__ sum, const int & k0);