diff options
Diffstat (limited to 'ggml.h')
| -rw-r--r-- | ggml.h | 115 |
1 files changed, 109 insertions, 6 deletions
@@ -211,6 +211,7 @@ #define GGML_MAX_OP_PARAMS 32 #define GGML_DEFAULT_N_THREADS 4 + #define GGML_EXIT_SUCCESS 0 #define GGML_EXIT_ABORTED 1 @@ -345,10 +346,12 @@ extern "C" { GGML_OP_ARGMAX, GGML_OP_REPEAT, GGML_OP_REPEAT_BACK, + GGML_OP_CONCAT, GGML_OP_SILU_BACK, GGML_OP_NORM, // normalize GGML_OP_RMS_NORM, GGML_OP_RMS_NORM_BACK, + GGML_OP_GROUP_NORM, GGML_OP_MUL_MAT, GGML_OP_OUT_PROD, @@ -374,14 +377,19 @@ extern "C" { GGML_OP_CLAMP, GGML_OP_CONV_1D, GGML_OP_CONV_2D, + GGML_OP_CONV_TRANSPOSE_2D, GGML_OP_POOL_1D, GGML_OP_POOL_2D, + GGML_OP_UPSCALE, // nearest interpolate + GGML_OP_FLASH_ATTN, GGML_OP_FLASH_FF, GGML_OP_FLASH_ATTN_BACK, GGML_OP_WIN_PART, GGML_OP_WIN_UNPART, + GGML_OP_GET_REL_POS, + GGML_OP_ADD_REL_POS, GGML_OP_UNARY, @@ -805,6 +813,13 @@ extern "C" { struct ggml_tensor * a, struct ggml_tensor * b); + // concat a and b on dim 2 + // used in stable-diffusion + GGML_API struct ggml_tensor * ggml_concat( + struct ggml_context * ctx, + struct ggml_tensor * a, + struct ggml_tensor * b); + GGML_API struct ggml_tensor * ggml_abs( struct ggml_context * ctx, struct ggml_tensor * a); @@ -913,6 +928,19 @@ extern "C" { struct ggml_tensor * a, float eps); + // group normalize along ne0*ne1*n_groups + // used in stable-diffusion + // TODO: eps is hardcoded to 1e-6 for now + GGML_API struct ggml_tensor * ggml_group_norm( + struct ggml_context * ctx, + struct ggml_tensor * a, + int n_groups); + + GGML_API struct ggml_tensor * ggml_group_norm_inplace( + struct ggml_context * ctx, + struct ggml_tensor * a, + int n_groups); + // a - x // b - dy // TODO: update with configurable eps @@ -1213,6 +1241,15 @@ extern "C" { float freq_base, float freq_scale); + // xPos RoPE, in-place, returns view(a) + GGML_API struct ggml_tensor * ggml_rope_xpos_inplace( + struct ggml_context * ctx, + struct ggml_tensor * a, + int n_past, + int n_dims, + float base, + bool down); + // rotary position embedding backward, i.e compute dx from dy // a - dy GGML_API struct ggml_tensor * ggml_rope_back( @@ -1221,7 +1258,11 @@ extern "C" { int n_past, int n_dims, int mode, - int n_ctx); + int n_ctx, + float freq_base, + float freq_scale, + float xpos_base, + bool xpos_down); // alibi position embedding // in-place, returns view(a) @@ -1248,6 +1289,15 @@ extern "C" { int p0, // padding int d0); // dilation + // conv_1d with padding = half + // alias for ggml_conv_1d(a, b, s, a->ne[0]/2, d) + GGML_API struct ggml_tensor* ggml_conv_1d_ph( + struct ggml_context * ctx, + struct ggml_tensor * a, + struct ggml_tensor * b, + int s, + int d); + GGML_API struct ggml_tensor * ggml_conv_2d( struct ggml_context * ctx, struct ggml_tensor * a, @@ -1259,14 +1309,38 @@ extern "C" { int d0, int d1); - // conv_1d with padding = half - // alias for ggml_conv_1d(a, b, s, a->ne[0]/2, d) - GGML_API struct ggml_tensor * ggml_conv_1d_ph( + + // kernel size is a->ne[0] x a->ne[1] + // stride is equal to kernel size + // padding is zero + // example: + // a: 16 16 3 768 + // b: 1024 1024 3 1 + // res: 64 64 768 1 + // used in sam + GGML_API struct ggml_tensor * ggml_conv_2d_sk_p0( + struct ggml_context * ctx, + struct ggml_tensor * a, + struct ggml_tensor * b); + + // kernel size is a->ne[0] x a->ne[1] + // stride is 1 + // padding is half + // example: + // a: 3 3 256 256 + // b: 64 64 256 1 + // res: 64 64 256 1 + // used in sam + GGML_API struct ggml_tensor * ggml_conv_2d_s1_ph( + struct ggml_context * ctx, + struct ggml_tensor * a, + struct ggml_tensor * b); + + GGML_API struct ggml_tensor * ggml_conv_transpose_2d_p0( struct ggml_context * ctx, struct ggml_tensor * a, struct ggml_tensor * b, - int s, - int d); + int stride); enum ggml_op_pool { GGML_OP_POOL_MAX, @@ -1293,6 +1367,13 @@ extern "C" { int p0, int p1); + // nearest interpolate + // used in stable-diffusion + GGML_API struct ggml_tensor * ggml_upscale( + struct ggml_context * ctx, + struct ggml_tensor * a, + int scale_factor); + GGML_API struct ggml_tensor * ggml_flash_attn( struct ggml_context * ctx, struct ggml_tensor * q, @@ -1346,6 +1427,27 @@ extern "C" { struct ggml_tensor * a, enum ggml_unary_op op); + // used in sam + GGML_API struct ggml_tensor * ggml_get_rel_pos( + struct ggml_context * ctx, + struct ggml_tensor * a, + int qh, + int kh); + + // used in sam + + GGML_API struct ggml_tensor * ggml_add_rel_pos( + struct ggml_context * ctx, + struct ggml_tensor * a, + struct ggml_tensor * pw, + struct ggml_tensor * ph); + + GGML_API struct ggml_tensor * ggml_add_rel_pos_inplace( + struct ggml_context * ctx, + struct ggml_tensor * a, + struct ggml_tensor * pw, + struct ggml_tensor * ph); + // custom operators typedef void (*ggml_unary_op_f32_t) (const int, float *, const float *); @@ -1500,6 +1602,7 @@ extern "C" { struct ggml_context * ctx, struct ggml_tensor * tensor); + GGML_API void ggml_build_forward_expand(struct ggml_cgraph * cgraph, struct ggml_tensor * tensor); GGML_API struct ggml_cgraph ggml_build_forward (struct ggml_tensor * tensor); |