b3922

llama : add infill sampler (#9896)

ggml-ci

b3184

ggml : synchronize threads using barriers (#7993)

b2938

Vulkan Embedding Fix (#7360)

* Fix empty Vulkan host buffers

Add fp32 fp16 matmul shader

Fix matmul shader alignment

* Remove deprecated tensor->backend uses

* Fix Vulkan validation errors on embedding models with no offloaded layers

* Fix Vulkan llava segfault when not offloading layers

b2898

Merge pull request #15 from ggerganov/master

push update

b2878

Revert "move ndk code to a new library (#6951)" (#7282)

This reverts commit efc8f767c8c8c749a245dd96ad4e2f37c164b54c.

b2872

Merge pull request #12 from JohannesGaessler/server-ngram-4

Server ngram 4

b2866

Merge pull request #10 from JohannesGaessler/cuda-fa-no-tc-11

Cuda fa no tc 11

b2861

cmake : fix version cmp (#7227)

b2843

llama-bench : add pp+tg test type (#7199)

b2633

Comment explaining a decision (#6531)