vendor : update cpp-httplib (ggml-org#19537)

Signed-off-by: Adrien Gallouët <[email protected]>

mtmd: Implement tiling for LFM2-VL (ggml-org#19454)

vulkan: disable coopmat1 fa on Nvidia Turing (ggml-org#19290)

vulkan: Optimize GGML_OP_CUMSUM (ggml-org#18417)

* vulkan: Optimize GGML_OP_CUMSUM

There are two paths: The preexisting one that does a whole row per workgroup
in a single shader, and one that splits each row into multiple blocks and does
two passes. The first pass computes partials within a block, the second adds
the block partials to compute the final result. The multipass shader is used
when there are a small number of large rows.

In the whole-row shader, handle multiple elements per invocation.

* use 2 ELEM_PER_THREAD for AMD/Intel

* address feedback

common : default content to an empty string (ggml-org#18485)

* common : default content to an empty string

* common : fix tests that break when content != null

webui: fix prompt progress ETA calculation (ggml-org#18468)

* webui: fix prompt progress ETA calculation

* handle case done === 0

server: enable jinja by default, update docs (ggml-org#17524)

* server: enable jinja by default, update docs

* fix tests

ci : disable AMD workflows + update NVIDIA workflows (ggml-org#16200)

* ci : disable AMD workflows + update NVIDIA workflows

* cont : fixes

* cont : update nvidia vulkan workflows

opencl: mark `argsort` unsupported if cols exceed workgroup limit (gg…

…ml-org#15375)

mtmd : clean up clip_n_output_tokens (ggml-org#15391)