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

12
ggml.h
View file

@ -1674,12 +1674,24 @@ extern "C" {
float p1);
// nearest interpolate
// multiplies ne0 and ne1 by scale factor
// used in stable-diffusion
GGML_API struct ggml_tensor * ggml_upscale(
struct ggml_context * ctx,
struct ggml_tensor * a,
int scale_factor);
// nearest interpolate
// nearest interpolate to specified dimensions
// used in tortoise.cpp
GGML_API struct ggml_tensor * ggml_upscale_ext(
struct ggml_context * ctx,
struct ggml_tensor * a,
int ne0,
int ne1,
int ne2,
int ne3);
// pad each dimension with zeros: [x, ..., x] -> [x, ..., x, 0, ..., 0]
GGML_API struct ggml_tensor * ggml_pad(
struct ggml_context * ctx,