thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

ggml webgpu: support for rope,div,sub,glu,scale,cont operators (#16187)

Browse source 
* Work on rope

* Simplify inplace operation generation and combine mul/add generation

* Work on rope variants

* implement neox rope

* rope complete

* Add sub,div,glu operators

* implement scale op

* Update cpy shader to handle cont/more types

* formatting

* Update test vars printing for rope,rms_norm

* Avoid ROPE hardcoded constants

* Add TODO to change ROPE constants to enum

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* fix TODO comment

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Reese Levine 2025-09-30 09:57:51 -07:00 • committed by GitHub
parent d1c84a662d
commit 8d78cd2613
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 1534 additions and 397 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/include/ggml.h
View file

@ -237,6 +237,8 @@
#define GGML_EXIT_SUCCESS 0
#define GGML_EXIT_ABORTED 1
// TODO: convert to enum https://github.com/ggml-org/llama.cpp/pull/16187#discussion_r2388538726
#define GGML_ROPE_TYPE_NORMAL 0
#define GGML_ROPE_TYPE_NEOX 2
#define GGML_ROPE_TYPE_MROPE 8
#define GGML_ROPE_TYPE_VISION 24