b4786

vulkan: matmul dequantization improvements (#12015)

* faster dequant for old quants

* dont use unpack for iq4_nl

* vec2 unpack for q8

b4784

cmake: Fix ggml backend dependencies and installation (#11818)

* Fix dependencies between ggml and backends

ggml backends link only to ggml-base and ggml links to all backends.

* Fix installation of ggml backends

Set up GNUInstallDirs before setting the installation directory of ggml backends

b4783

llava : add struct for FFI bindgen (#12079)

* add struct for FFI bindgen

* Apply suggestions from code review

---------

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

b4778

vulkan: fix assertion when qy_needs_dequant (#12068)

Looks like a copy/paste bug from qx_needs_dequant.

b4777

server: handle echo=false on /v1/completions (#12060)

b4776

add OP sigmoid (#12056)

Co-authored-by: Judd <[email protected]>

b4775

ggml-cpu: Fix build with sve (#12059)

* ggml-cpu: Fix build with sve

Signed-off-by: Molly Sophia <[email protected]>

* ggml-cpu: Remove unused variable in sve q3_k vec dot

Signed-off-by: Molly Sophia <[email protected]>

---------

Signed-off-by: Molly Sophia <[email protected]>

b4774

vulkan: implement more backpropagation operators (#11914)

* vulkan: implement GGML_OP_ROPE_BACK

* vulkan: implement GGML_OP_RMS_NORM_BACK

* vulkan: implement GGML_OP_SILU_BACK

* vulkan: implement GGML_OP_SOFTMAX_BACK

b4773

server: support add_generation_prompt query param (#12062)

b4771

llama : expose llama_model_n_head_kv in the API (#11997)

It's useful to be able to have this from the library layer as it's a key
parameter of the model (e.g. to figure out how much KV cache memory is
needed).