codeowners : update + cleanup (#16174)

---------

Co-authored-by: slaren <slarengh@gmail.com>

scripts/ci-run.sh

@@ -1,50 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-this=$(realpath "$0"); readonly this
-cd "$(dirname "$this")"
-shellcheck "$this"
-
-if (( $# != 1 && $# != 2  )); then
-    cat >&2 <<'EOF'
-usage:
-    ci-run.sh <tmp_dir> [<cache_dir>]
-
-This script wraps ci/run.sh:
-* If <tmp_dir> is a ramdisk, you can reduce writes to your SSD. If <tmp_dir> is not a ramdisk, keep in mind that total writes will increase by the size of <cache_dir>.
-    (openllama_3b_v2: quantized models are about 30GB)
-* Persistent model and data files are synced to and from <cache_dir>,
-    excluding generated .gguf files.
-    (openllama_3b_v2: persistent files are about 6.6GB)
-* <cache_dir> defaults to  ~/.cache/llama.cpp
-EOF
-    exit 1
-fi
-
-cd .. # => llama.cpp repo root
-
-tmp="$1"
-mkdir -p "$tmp"
-tmp=$(realpath "$tmp")
-echo >&2 "Using tmp=$tmp"
-
-cache="${2-$HOME/.cache/llama.cpp}"
-mkdir -p "$cache"
-cache=$(realpath "$cache")
-echo >&2 "Using cache=$cache"
-
-_sync() {
-    local from="$1"; shift
-    local to="$1"; shift
-
-    echo >&2 "Syncing from $from to $to"
-    mkdir -p "$from" "$to"
-    rsync -a "$from" "$to" --delete-during "$@"
-}
-
-_sync "$(realpath .)/" "$tmp/llama.cpp"
-_sync "$cache/ci-mnt/models/" "$tmp/llama.cpp/ci-mnt/models/"
-
-cd "$tmp/llama.cpp"
-bash ci/run.sh ci-out ci-mnt
-
-_sync 'ci-mnt/models/' "$cache/ci-mnt/models/" --exclude='*.gguf' -P

scripts/qnt-all.sh

@@ -1,30 +0,0 @@
-#!/usr/bin/env bash
-
-qnt=(q8_0 q6_k q5_k q5_1 q5_0 q4_k q4_1 q4_0 q3_k q2_k)
-args=""
-
-if [ -z "$1" ]; then
-    echo "usage: $0 <model> [qnt] [args]"
-    echo "default: $0 <model> \"${qnt[@]}\" \"${args}\""
-    exit 1
-fi
-
-if [ ! -z "$2" ]; then
-    qnt=($2)
-fi
-
-if [ ! -z "$3" ]; then
-    args="$3"
-fi
-
-model="$1"
-out="../tmp/results-${model}"
-
-set -o pipefail
-set -e
-
-mkdir -p ${out}
-
-for q in ${qnt[@]}; do
-    time ./bin/llama-quantize ../models/${model}/ggml-model-f16.gguf ../models/${model}/ggml-model-${q}.gguf ${q} 2>&1 ${args} | tee ${out}/qnt-${q}.txt
-done

scripts/run-all-perf.sh

@@ -1,34 +0,0 @@
-#!/usr/bin/env bash
-
-qnt=(f16 q8_0 q6_k q5_k q5_1 q5_0 q4_k q4_1 q4_0 q3_k q2_k)
-args="-ngl 999 -n 64 -p 512"
-
-if [ -z "$1" ]; then
-    echo "usage: $0 <model> [qnt] [args]"
-    echo "default: $0 <model> \"${qnt[@]}\" \"${args}\""
-    exit 1
-fi
-
-if [ ! -z "$2" ]; then
-    qnt=($2)
-fi
-
-if [ ! -z "$3" ]; then
-    args="$3"
-fi
-
-model="$1"
-out="../tmp/results-${model}"
-
-set -o pipefail
-set -e
-
-mkdir -p ${out}
-
-mstr=""
-
-for q in ${qnt[@]}; do
-    mstr="${mstr} -m ../models/${model}/ggml-model-${q}.gguf"
-done
-
-./bin/llama-bench ${mstr} ${args} 2> /dev/null

scripts/run-all-ppl.sh

@@ -1,30 +0,0 @@
-#!/usr/bin/env bash
-
-qnt=(f16 q8_0 q6_k q5_k q5_1 q5_0 q4_k q4_1 q4_0 q3_k q2_k)
-args="-ngl 999 -t 8"
-
-if [ -z "$1" ]; then
-    echo "usage: $0 <model> [qnt] [args]"
-    echo "default: $0 <model> \"${qnt[@]}\" \"${args}\""
-    exit 1
-fi
-
-if [ ! -z "$2" ]; then
-    qnt=($2)
-fi
-
-if [ ! -z "$3" ]; then
-    args="$3"
-fi
-
-set -o pipefail
-set -e
-
-model="$1"
-out="../tmp/results-${model}"
-
-mkdir -p ${out}
-
-for q in ${qnt[@]}; do
-    time ./bin/llama-perplexity -m ../models/${model}/ggml-model-f16.gguf -f ./wiki.test.raw ${args} 2>&1 | tee ${out}/ppl-${q}.txt
-done