b5646

server : re-enable SWA speculative decoding (#14131)

ggml-ci

b5645

context : simplify output counting logic during decode (#14142)

* batch : remove logits_all flag

ggml-ci

* context : simplify output counting logic during decode

ggml-ci

* cont : fix comments

b5644

batch : remove logits_all flag (#14141)

ggml-ci

b5642

kv-cache : fix split_equal handling in unified implementation (#14130)

ggml-ci

b5641

context : round n_tokens to next multiple of n_seqs when reserving (#…

b5640

common: fix issue with regex_escape routine on windows (#14133)

b5639

Implement GGML_CPU_ALL_VARIANTS for ARM (#14080)

* ggml-cpu: Factor out feature detection build from x86

* ggml-cpu: Add ARM feature detection and scoring

This is analogous to cpu-feats-x86.cpp. However, to detect compile-time
activation of features, we rely on GGML_USE_<FEAT> which need to be set
in cmake, instead of GGML_<FEAT> that users would set for x86.

This is because on ARM, users specify features with GGML_CPU_ARM_ARCH,
rather than with individual flags.

* ggml-cpu: Implement GGML_CPU_ALL_VARIANTS for ARM

Like x86, however to pass around arch flags within cmake, we use
GGML_INTERNAL_<FEAT> as we don't have GGML_<FEAT>.

Some features are optional, so we may need to build multiple backends
per arch version (armv8.2_1, armv8.2_2, ...), and let the scoring
function sort out which one can be used.

* ggml-cpu: Limit ARM GGML_CPU_ALL_VARIANTS to Linux for now

The other platforms will need their own specific variants.

This also fixes the bug that the the variant-building branch was always
being executed as the else-branch of GGML_NATIVE=OFF. The branch is
moved to an elseif-branch which restores the previous behavior.

b5638

chore : clean up relative source dir paths (#14128)

b5637

tests : add test-tokenizers-repo (#14017)

b5636

vulkan: Better thread-safety for command pools/buffers (#14116)

This change moves the command pool/buffer tracking into a vk_command_pool
structure. There are two instances per context (for compute+transfer) and
two instances per device for operations that don't go through a context.
This should prevent separate contexts from stomping on each other.