cuda : disable host register by default (ggml-org#6206)

tests : disable system() calls (ggml-org#6198)

ggml-ci

Add ability to use Q5_0, Q5_1, and IQ4_NL for quantized K cache (ggml…

…-org#6183)

* k_cache: be able to use Q5_0

* k_cache: be able to use Q5_1 on CODA

* k_cache: be able to use Q5_0 on Metal

* k_cache: be able to use Q5_1 on Metal

* k_cache: be able to use IQ4_NL - just CUDA for now

* k_cache: be able to use IQ4_NL on Metal

* k_cache: add newly added supported types to llama-bench and CUDA supports_op

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

Add nvidia and amd backends (ggml-org#6157)

cuda : fix conflict with std::swap (ggml-org#6186)

cuda : print the returned error when CUDA initialization fails (ggml-…

…org#6185)

llava : add MobileVLM_V2 backup (ggml-org#6175)

* Add MobileVLM_V2 backup

* Update MobileVLM-README.md

* Update examples/llava/MobileVLM-README.md

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/llava/convert-image-encoder-to-gguf.py

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* clip :  fix whitespace

* fix deifinition mistake in clip.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

cuda : refactor to remove global resources (ggml-org#6170)

* cuda : refactor to remove global resources

Server: version bump for httplib and json (ggml-org#6169)

* server: version bump for httplib and json

* fix build

* bring back content_length

Revert "llava : add a MobileVLM_V2-1.7B backup (ggml-org#6152)"

This reverts commit f8c4e74.