haraldwolff
/
whisper.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Vulkan Improvements (llama/5835) 

* Improve dequant shaders, add fast q4_0 dequant

* Optimize dmmv non-kquants for GCN

Remove unnecessary SPIR-V shader duplication

* Fix q4_0 dequant dispatch sizes

Fix backend free bug

* Optimize dequant shaders for q4_1, q5_0, q5_1 and q8_0

* Add unary and binary op shader templates

* Fix Vulkan check results

* Enable non-contiguous support for simple ops

* Add argsort

Basic q4_0 mmq shader and unit test

* Speed up q4_0 dequant code, enable mmq for q4_0

* Rework matmul pipeline selection

* Add soft_max alibi support

* Add q4_1, q5_0, q5_1 and q8_0 dequant mat mat mul shaders

* Add environment variable GGML_VK_FORCE_MAX_ALLOCATION_SIZE to limit max buffer size

Rename GGML_VULKAN_DISABLE_F16 to GGML_VK_DISABLE_F16 for consistency
pull/1943/head
0cc4m 2024-03-05 13:33:42 +01:00 committed by Georgi Gerganov
parent 9d9a405cfd
commit 9c399689ec
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
2 changed files with 1341 additions and 788 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2128
ggml-vulkan.cpp
View File

File diff suppressed because it is too large Load Diff

1
ggml-vulkan.h
View File

@ -10,6 +10,7 @@ extern "C" {
#define GGML_VK_NAME "Vulkan"
#define GGML_VK_MAX_DEVICES 16
GGML_API void ggml_vk_instance_init(void);
GGML_API void ggml_vk_init_cpu_assist(void);
GGML_API void ggml_vk_preallocate_buffers_graph_cpu_assist(struct ggml_tensor * node);