parent
2fffa0d61f
commit
183b3fac6c
2 changed files with 40 additions and 33 deletions
57
ggml-metal.m
57
ggml-metal.m
|
@ -1419,34 +1419,35 @@ void ggml_metal_graph_compute(
|
|||
default: GGML_ASSERT(false);
|
||||
};
|
||||
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:2];
|
||||
[encoder setBytes:&ne00 length:sizeof( int64_t) atIndex:3];
|
||||
[encoder setBytes:&ne01 length:sizeof( int64_t) atIndex:4];
|
||||
[encoder setBytes:&ne02 length:sizeof( int64_t) atIndex:5];
|
||||
[encoder setBytes:&ne03 length:sizeof( int64_t) atIndex:6];
|
||||
[encoder setBytes:&nb00 length:sizeof(uint64_t) atIndex:7];
|
||||
[encoder setBytes:&nb01 length:sizeof(uint64_t) atIndex:8];
|
||||
[encoder setBytes:&nb02 length:sizeof(uint64_t) atIndex:9];
|
||||
[encoder setBytes:&nb03 length:sizeof(uint64_t) atIndex:10];
|
||||
[encoder setBytes:&ne0 length:sizeof( int64_t) atIndex:11];
|
||||
[encoder setBytes:&ne1 length:sizeof( int64_t) atIndex:12];
|
||||
[encoder setBytes:&ne2 length:sizeof( int64_t) atIndex:13];
|
||||
[encoder setBytes:&ne3 length:sizeof( int64_t) atIndex:14];
|
||||
[encoder setBytes:&nb0 length:sizeof(uint64_t) atIndex:15];
|
||||
[encoder setBytes:&nb1 length:sizeof(uint64_t) atIndex:16];
|
||||
[encoder setBytes:&nb2 length:sizeof(uint64_t) atIndex:17];
|
||||
[encoder setBytes:&nb3 length:sizeof(uint64_t) atIndex:18];
|
||||
[encoder setBytes:&n_past length:sizeof( int) atIndex:19];
|
||||
[encoder setBytes:&n_dims length:sizeof( int) atIndex:20];
|
||||
[encoder setBytes:&mode length:sizeof( int) atIndex:21];
|
||||
[encoder setBytes:&freq_base length:sizeof(float) atIndex:22];
|
||||
[encoder setBytes:&freq_scale length:sizeof(float) atIndex:23];
|
||||
[encoder setBytes:&ext_factor length:sizeof(float) atIndex:24];
|
||||
[encoder setBytes:&attn_factor length:sizeof(float) atIndex:25];
|
||||
[encoder setBytes:&beta_fast length:sizeof(float) atIndex:26];
|
||||
[encoder setBytes:&beta_slow length:sizeof(float) atIndex:27];
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:2];
|
||||
[encoder setBytes:&ne00 length:sizeof( int64_t) atIndex:3];
|
||||
[encoder setBytes:&ne01 length:sizeof( int64_t) atIndex:4];
|
||||
[encoder setBytes:&ne02 length:sizeof( int64_t) atIndex:5];
|
||||
[encoder setBytes:&ne03 length:sizeof( int64_t) atIndex:6];
|
||||
[encoder setBytes:&nb00 length:sizeof(uint64_t) atIndex:7];
|
||||
[encoder setBytes:&nb01 length:sizeof(uint64_t) atIndex:8];
|
||||
[encoder setBytes:&nb02 length:sizeof(uint64_t) atIndex:9];
|
||||
[encoder setBytes:&nb03 length:sizeof(uint64_t) atIndex:10];
|
||||
[encoder setBytes:&ne0 length:sizeof( int64_t) atIndex:11];
|
||||
[encoder setBytes:&ne1 length:sizeof( int64_t) atIndex:12];
|
||||
[encoder setBytes:&ne2 length:sizeof( int64_t) atIndex:13];
|
||||
[encoder setBytes:&ne3 length:sizeof( int64_t) atIndex:14];
|
||||
[encoder setBytes:&nb0 length:sizeof(uint64_t) atIndex:15];
|
||||
[encoder setBytes:&nb1 length:sizeof(uint64_t) atIndex:16];
|
||||
[encoder setBytes:&nb2 length:sizeof(uint64_t) atIndex:17];
|
||||
[encoder setBytes:&nb3 length:sizeof(uint64_t) atIndex:18];
|
||||
[encoder setBytes:&n_past length:sizeof( int) atIndex:19];
|
||||
[encoder setBytes:&n_dims length:sizeof( int) atIndex:20];
|
||||
[encoder setBytes:&mode length:sizeof( int) atIndex:21];
|
||||
[encoder setBytes:&n_orig_ctx length:sizeof( int) atIndex:22];
|
||||
[encoder setBytes:&freq_base length:sizeof( float) atIndex:23];
|
||||
[encoder setBytes:&freq_scale length:sizeof( float) atIndex:24];
|
||||
[encoder setBytes:&ext_factor length:sizeof( float) atIndex:25];
|
||||
[encoder setBytes:&attn_factor length:sizeof( float) atIndex:26];
|
||||
[encoder setBytes:&beta_fast length:sizeof( float) atIndex:27];
|
||||
[encoder setBytes:&beta_slow length:sizeof( float) atIndex:28];
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(ne01, ne02, ne03) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
|
||||
} break;
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue