llama : replacing auto &kv with const auto &kv (ggml-org#2041)

* Replacing auto &kv with const auto &kv

* Create codacy.yml

* Delete codacy.yml

llama : remove shards weight file support (ggml-org#2000)

* Remove multiple shards

* Remove multiple file loaders

* Remove llama_load_tensor_shard class

* Simplify load logic

* Remove dead code guess_n_parts function

* Remove vocab_only from constructor of llama_model_loader

* Remove alignment_prevents_mmap which is not more needed.

* Remove useless check

cuda : fix missing const qualifier in casts (ggml-org#2027)

CUDA GPU acceleration for LoRAs + f16 models (ggml-org#1970)

cuda : remove nchannels_x argument from mul_mat_vec_nc_f16_f32 (ggml-…

…org#2028)

- Not used

fix pthreads setaffinity usage on android (ggml-org#2020)

baby-llama : fix build after ggml_rope change (ggml-org#2016)

ggml : increase max tensor name + clean up compiler warnings in train…

…-text (ggml-org#1988)

* Clean up compiler warnings in train-text

Some brackets to disambiguate order of operations

* Increase GGML_MAX_NAME

Avoiding strncpy danger in train-text-from-scratch and reducing potential future name length issues

Fix assert when free invalid cuda pointer (ggml-org#2005)

Fix assert via initializing extra structure always.
CUDA error 1 at C:\GPT\llama.cpp\ggml-cuda.cu:2536: invalid argument

ggml : avoid conv 2d kernel round up