llama-bench : add embeddings option (ggml-org#5924)

* llama-bench : add embeddings option

* llama-bench : do not hard code embd default value

---------

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

cmake : fix VULKAN and ROCm builds (ggml-org#5525)

* cmake : fix VULKAN and ROCm builds

* cmake : fix (cont)

* vulkan : fix compile warnings

ggml-ci

* cmake : fix

ggml-ci

* cmake : minor

ggml-ci

add --no-mmap in llama-bench (ggml-org#5257)

* add --no-mmap, show sycl backend

* fix conflict

* fix code format, change print for --no-mmap

* ren no_mmap to mmap, show mmap when not default value in printer

* update guide for mmap

* mv position to reduce model reload

nix-shell: use addToSearchPath

thx to @SomeoneSerge for the suggestion!

common : fix the short form of `--grp-attn-w`, not `-gat` (ggml-org#4825

)

See https://github.com/ggerganov/llama.cpp/blob/master/common/common.cpp#L230C53-L230C57

server : send token probs for "stream == false" (ggml-org#4714)

train : fix typo in overlapping-samples help msg (ggml-org#4758)

This commit fixes a typo in the help message for the
--overlapping-samples option.

Signed-off-by: Daniel Bevenius <[email protected]>

cuda : simplify expression

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

gpt2 : Add gpt2 architecture integration (ggml-org#4555)

llama : add AWQ for llama, llama2, mpt, and mistral models (ggml-org#…

…4593)

* update: awq support llama-7b model

* update: change order

* update: benchmark results for llama2-7b

* update: mistral 7b v1 benchmark

* update: support 4 models

* fix: Readme

* update: ready for PR

* update: readme

* fix: readme

* update: change order import

* black

* format code

* update: work for bot mpt and awqmpt

* update: readme

* Rename to llm_build_ffn_mpt_awq

* Formatted other files

* Fixed params count

* fix: remove code

* update: more detail for mpt

* fix: readme

* fix: readme

* update: change folder architecture

* fix: common.cpp

* fix: readme

* fix: remove ggml_repeat

* update: cicd

* update: cicd

* uppdate: remove use_awq arg

* update: readme

* llama : adapt plamo to new ffn

ggml-ci

---------

Co-authored-by: Trần Đức Nam <[email protected]>
Co-authored-by: Le Hoang Anh <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>