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

ggml : add ggml_upscale_ext (ggml/814)

Browse source 
* initial commit with CPU implementation of upscale to shape and test, cuda implementation next

* experimental commit to see if dst shape is correct

* test version

* test

* removed unnecessary params

* refactor

* fixed tests

* ggml : metal impl + cleanup + sycl dev warnings

* patched ggml_upscale cuda op to handle non-contiguous tensors, added test for non-contiguous behavior

* metal : fix upsacle op to support nb00 + style

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
John Balis 2024-05-15 03:52:33 -05:00 • committed by Georgi Gerganov
parent 583fd6b000
commit 48aa8fd1f2
No known key found for this signature in database
GPG key ID: BF970631944C16B7
7 changed files with 146 additions and 60 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ggml-sycl.cpp
View file

@ -13987,6 +13987,10 @@ inline void ggml_sycl_op_upscale(const ggml_tensor *src0,
GGML_ASSERT(dst->type == GGML_TYPE_F32);
GGML_ASSERT(src0->ne[3] == 1 && dst->ne[3] == 1); // just 3D tensors
#pragma message("TODO: generalize upscale operator")
#pragma message(" https://github.com/ggerganov/ggml/pull/814")
GGML_ASSERT(false && "TODO: generalize upscale operator);
const int scale_factor = dst->op_params[0];
upscale_f32_sycl(src0_dd, dst_dd, src0->ne[0], src0->ne[1], src0->ne[2], scale_factor, main_stream);