GitLab

This will speed up CI which already tries to only build static for unit tests

Fix target in gen_windows.ps1

fix gemma, command-r layer weights

These are useful outside this package.

check file type before zip

use merge base for diff-tree

Also, remove a superfluous 'go get'

Put back non-avx CPU build for windows

Fixed a typo

Bump llama.cpp to b2737

Fix exe name for zip packaging on windows

The zip file encodes the OS and architecture, so keep the short exe name

Refactor windows generate for more modular usage

Move cuda/rocm dependency gathering into generate script

This will make it simpler for CI to accumulate artifacts from prior steps

Fix release CI

download-artifact path was being used incorrectly.  It is where to
extract the zip not the files in the zip to extract.  Default is
workspace dir which is what we want, so omit it

only count output tensors

Improve mac parallel performance

* reload model if `num_gpu` changes

* dont reload on -1

* fix tests

* llm: limit generation to 10x context size to avoid run on generations

* add comment

* simplify condition statement

Move ggml loading to when attempting to fit