b6058

model : add hunyuan dense (#14878)

* support hunyuan_v1_dense

Signed-off-by: stevenkuang <[email protected]>

* update hunyuan_moe to hunyuan_v1_moe

Signed-off-by: stevenkuang <[email protected]>

* fix rope alpha assert and bos token

Signed-off-by: stevenkuang <[email protected]>

* add blank line

Signed-off-by: stevenkuang <[email protected]>

* Revert "update hunyuan_moe to hunyuan_v1_moe"

This reverts commit aa973ca21913aba77f6e81a935270ef7be222e75.

* use hunyuan_dense instead of hunyuan_v1_dense

Signed-off-by: stevenkuang <[email protected]>

* fix hunyuan_moe chat template

Signed-off-by: stevenkuang <[email protected]>

* remove leftover code

Signed-off-by: stevenkuang <[email protected]>

* update hunyuan dense chat template

Signed-off-by: stevenkuang <[email protected]>

* fix hunyuan dense vocab and chat template

Signed-off-by: stevenkuang <[email protected]>

---------

Signed-off-by: stevenkuang <[email protected]>

b6057

opencl: add f16 for `add`, `sub`, `mul`, `div` (#14984)

b6056

ggml : Q2k interleaving implementation - x86/x64 SIMD (#14373)

* Initial Q2_K Block Interleaving Implementation

* Addressed review comments and clean up of the code

* Post rebase fixes

* Initial CI/CD fixes

* Update declarations in arch-fallback.h

* Changes for GEMV Q2_K in arch-fallback.h

* Enable repacking only on AVX-512 machines

* Update comments in repack.cpp

* Address q2k comments

---------

Co-authored-by: Manogna-Sree <[email protected]>

b6055

graph : fix equal_seq() check (#14986)

ggml-ci

b6054

docker : add cann build pipline (#14591)

* docker: add cann build pipline

* docker: add cann build pipline

* docker: fix cann devops

* cann : fix multi card hccl

* Update ggml/src/ggml-cann/ggml-cann.cpp

Co-authored-by: Xuan-Son Nguyen <[email protected]>

* Update ggml-cann.cpp

---------

Co-authored-by: Georgi Gerganov <[email protected]>
Co-authored-by: Xuan-Son Nguyen <[email protected]>

b6052

quantize : skip tensor override when in fallback mode (#14995)

b6051

llama : add simple option to enable CPU for MoE weights (--cpu-moe) (…

b6050

Fix params bug in diffusion example (#14993)

b6049

llama : allow other bufts when overriding to CPU, add --no-repack opt…

b6048

Vulkan: Fix minor debug mode issues (#14899)

* vulkan: fix debug mode issues

* vulkan: remove broken check_results GGML_OP_SET_ROWS support