b2950

rpc : track allocated buffers (#7411)

* rpc : track allocated buffers

ref: #7407

* rpc : pack rpc_tensor tightly

b2949

server : fix temperature + disable some tests (#7409)

* server : fix temperature

* server : disable tests relying on parallel determinism

* ci : change server Debug -> RelWithDebInfo

b2948

[SYCL] Update SYCL upscale operation (#7321)

* Update SYCL upscale operation

* Formatting

* Remove messages

b2946

ggml-opencl, llama: using reserve() if count already known (#7272)

b2945

ggml : add loongarch lsx and lasx support (#6454)

* add loongarch lsx and lasx optimize code

* Add loongarch compilation support to makefile

* revert stb_image.h

* opt bytes_from_nibbles_32 and sum_i16_pairs_float

* fix undeclared

* format code

* update

* update 2

---------

Co-authored-by: Jinyang He <[email protected]>

b2943

server : return error on too large embedding input (#7389)

b2941

Add provisions for windows support for BF16 code including CMake prov…

b2940

llama : remove MPI backend (#7395)

b2939

quantize : fix --keep-split check (#7374)

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