server : fix handling of characters that span multiple tokens when st…

…reaming (ggml-org#4446)

common : add `--version` option to show build info in CLI (ggml-org#4433

)

gguf-py : export chat templates (ggml-org#4125)

* gguf-py : export chat templates

* llama.cpp : escape new lines in gguf kv info prints

* gguf-py : bump version

* gguf-py : check chat_template type

* gguf-py : initialize chat_template

flake : update flake.lock for newer transformers version + provide ex…

…tra dev shell (ggml-org#3797)

* flake : update flake.lock for newer transformers version + provide extra dev shell with torch and transformers (for most convert-xxx.py scripts)

CLBlast: Add outer loops over src0 for broadcasting in mulmat

Reduce repeated dequantization of the same data.

multimodal : add BakLLaVA conversion support (ggml-org#3682)

CLBlast: Add outer loops over src0 for broadcasting in mulmat

Reduce repeated dequantization of the same data.

speculative : bug fixes

opencl : fix element-wise multiplication (ggml-org#3656)

CLBlast: Fix temporary buffer size for f16 conversion (wsize)

Fix buffer overflow.
Reduce the size to fit just one 2D slice.
Assert sufficient size.