vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : generalize GGML_OP_CONCAT (#7563)

Browse source 
* ggml : generalize GGML_OP_CONCAT (WIP)

ggml-ci

* tests : add dim != 2 tests

* metal : generalize concat kernel

* tests : naming

* cuda : generalize concat kernel

ggml-ci

* sycl : add warning and assert

* ggml : fix op params handling

* metal : bugfix kernel

ggml-ci

* ggml : reimplement CPU and Metal

* cuda : add asserts

ggml-ci

* ggml : fix ptrs

ggml-ci
This commit is contained in:
Georgi Gerganov 2024-05-28 11:04:19 +03:00 • committed by GitHub
parent 9335b969e8
commit 0548a4187f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 167 additions and 56 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml-metal.m
View file

@ -990,6 +990,8 @@ static enum ggml_status ggml_metal_graph_compute(
{
id<MTLComputePipelineState> pipeline = ctx->kernels[GGML_METAL_KERNEL_TYPE_CONCAT].pipeline;
const int32_t dim = ((int32_t *) dst->op_params)[0];
[encoder setComputePipelineState:pipeline];
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
[encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
@ -1018,6 +1020,7 @@ static enum ggml_status ggml_metal_graph_compute(
[encoder setBytes:&nb1 length:sizeof(nb1) atIndex:24];
[encoder setBytes:&nb2 length:sizeof(nb2) atIndex:25];
[encoder setBytes:&nb3 length:sizeof(nb3) atIndex:26];
[encoder setBytes:&dim length:sizeof(dim) atIndex:27];
const int nth = MIN(1024, ne0);