b4006

ggml : remove ggml_scratch (#10121)

ggml-ci

b4005

sync : ggml

b4003

build: fix build error in Windows env with OneAPI setup (#10107)

b4002

llama : improve output buffer type selection (#10098)

b4001

quantize : fix --keep-split (#10114)

b4000

llama : fix buffer checks for mamba and rwk (#10111)

* llama : fix buffer checks for mamba and rwk

* llama : fix missing worst case flag during reserve

* cuda : fix supports_op for norm

* disable sched SET_CAUSE

b3999

loader:  refactor tensor weights storage (#9935)

* loader: refactor tensor weights storage

* use sorted map, sort weights by layer

---------

Co-authored-by: slaren <slarengh@gmail.com>

b3998

server : include scheme when printing URL (#10106)

b3997

ggml : check tensor name lengths in gguf files (#10100)

b3996

kompute: add mul_mat_q4_k shader (#10097)

This is a more or less direct translation from the Metal implementation
to GLSL.

Signed-off-by: Sergio Lopez <slp@redhat.com>