whisper.cpp / ggml-vulkan.cpp

Commit History

Vulkan Shader Refactor, Memory Debugging Option (llama/7947)
d0120b1

OccamRazor commited on

move BLAS to a separate backend (llama/6210)
c773aa9

slaren ggerganov commited on

tests : add non-cont unary tests (llama/7857)
6dc2887

ggerganov commited on

vulkan: select only one device for single gpu with multiple drivers (llama/7582)
ee56a37

Adriankhl commited on

Update Vulkan RoPE implementation (llama/7818)
71850e7

OccamRazor slaren commited on

vulkan : reuse parent extra for views (llama/7806)
b9b60de

slaren OccamRazor commited on

ggml : refactor rope norm/neox (llama/7634)
ded0c68

ggerganov commited on

Vulkan Mixture of Experts (MoE) support (llama/7628)
ad9ee26

OccamRazor commited on

vulkan: properly initialize vulkan devices for LLAMA_SPLIT_MODE_NONE (llama/7552)
da90a1e

Adriankhl commited on

Update vulkan rope implementation to support frequency factors (llama/7475)
be0ec58

OccamRazor commited on

llama : add phi3 128K model support (llama/7225)
ef68527

liuwei-git ggerganov commited on

Vulkan Embedding Fix (llama/7360)
2bfeba3

OccamRazor commited on

Update and fix Vulkan soft_max and argsort implementations (llama/7237)
a0218a3

OccamRazor commited on

ggml : full ALiBi support (llama/7192)
192bda4

ggerganov commited on

Vulkan Bugfixes and Improvements (llama/7084)
8dade62

OccamRazor commited on

Vulkan k-quant mmq and ggml-backend offload functionality (llama/6155)
1ff7b08
unverified

OccamRazor commited on

sync : ggml (#2001)
cbbfa9e
unverified

ggerganov commited on

llama : add pipeline parallelism support (llama/6017)
b5bb3f3
unverified

slaren compilade ggerganov commited on

ggml : remove old quantization functions (llama/5942)
11a2545
unverified

ggerganov commited on

Vulkan Improvements (llama/5835)
ea2da45
unverified

OccamRazor commited on

ggml : introduce ggml_status (ggml/750)
151c676
unverified

Michael Podvitskiy slaren ggerganov commited on

ggml-vulkan: fix VULKAN_CHECK_RESULTS flag, which was previously broken (llama/5813)
472195f
unverified

ddpasa commited on

make portability_enumeration_ext apple only (llama/5757)
c164918
unverified

Eve commited on

code : normalize enum names (llama/5697)
93e0830
unverified

ggerganov commited on

Introduce backend GUIDs (ggml/743)
a7eb9f6
unverified

UEXTM.com slaren commited on

Refactor validation and enumeration platform checks into functions to clean up ggml_vk_instance_init()
8637c17
unverified

OccamRazor commited on

Add check for VK_KHR_portability_enumeration for MoltenVK support
85caa3f
unverified

OccamRazor commited on

Add preprocessor checks for Apple devices.
b8e3b87
unverified

dokterbob commited on

Resolve ErrorIncompatibleDriver with Vulkan on MacOS.
0bc3433
unverified

dokterbob commited on

cmake : fix VULKAN and ROCm builds (llama/5525)
ae570e4
unverified

ggerganov commited on

vulkan: Find optimal memory type but with fallback (llama/5381)
24e2319
unverified

lcfrs commited on

vulkan: only use M-sized matmul on Apple GPUs (llama/5412)
350284e
unverified

Sergio López commited on

src : relocate new backend sources
44cd2d4
unverified

ggerganov commited on