ggml : multi-thread ggml_rope() (~3-4 times faster on M1) (ggml-org#781)

ggml, llama : avoid heavy V transpose + improvements (ggml-org#775)

ggml :

- added ggml_view_3d()
- ggml_view_tensor() now inherits the stride too
- reimplement ggml_cpy() to account for dst stride
- no longer require tensor->data to be memory aligned

llama :

- compute RoPE on 32-bit tensors (should be more accurate)
- store RoPE-ed K in the KV cache
- store transposed V in the KV cache (significant speed-up)
- avoid unnecessary Q copy

llama : define non-positive top_k; top_k range check (ggml-org#779)

* Define non-positive top_k; top_k range check

* minor : brackets

---------

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

make : missing host optimizations in CXXFLAGS (ggml-org#763)

Define non-positive temperature behavior (ggml-org#720)

10+% performance improvement of ggml_vec_dot_q4_0 on AVX2 (ggml-org#654)

* Performance improvement of AVX2 code
* Fixed problem with MSVC compiler
* Reviewer comments: removed double semicolon, deleted empty line 1962

Windows: reactive sigint handler after each Ctrl-C (ggml-org#736)

Added api for getting/setting the kv_cache (ggml-org#685)

The api provides access methods for retrieving the current memory buffer for the kv_cache and its token number.
It also contains a method for setting the kv_cache from a memory buffer.

This makes it possible to load/save history - maybe support --cache-prompt paramater as well?

Co-authored-by: Pavol Rusnak <[email protected]>

make : use -march=native -mtune=native on x86 (ggml-org#609)

ggml : change ne to int64_t (ggml-org#626)