diff --git a/scripts/snapdragon/windows/run-cli.ps1 b/scripts/snapdragon/windows/run-cli.ps1 index 40c7acc430..5891c894a9 100644 --- a/scripts/snapdragon/windows/run-cli.ps1 +++ b/scripts/snapdragon/windows/run-cli.ps1 @@ -46,8 +46,8 @@ if ($null -ne $env:NDEV) { $env:ADSP_LIBRARY_PATH="$basedir\lib" -& "$basedir\bin\llama-completion.exe" ` - --no-mmap -no-cnv -m $basedir\..\..\gguf\$model ` +& "$basedir\bin\llama-cli.exe" ` + --no-mmap -m $basedir\..\..\gguf\$model ` --poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1 ` --ctx-size 8192 --ubatch-size 128 -fa on ` -ngl 99 --device $device $cli_opts diff --git a/scripts/snapdragon/windows/run-completion.ps1 b/scripts/snapdragon/windows/run-completion.ps1 new file mode 100644 index 0000000000..8a48d2d748 --- /dev/null +++ b/scripts/snapdragon/windows/run-completion.ps1 @@ -0,0 +1,53 @@ + +#!/usr/bin/env pwsh + +# Basedir on device +$basedir=".\pkg-snapdragon" + +$cli_opts=$args + +$model="Llama-3.2-3B-Instruct-Q4_0.gguf" +if ($null -ne $env:M) { + $model=$env:M +} + +$device="HTP0" +if ($null -ne $env:D) { + $device=$env:D +} + +if ($null -ne $env:V) { + $env:GGML_HEXAGON_VERBOSE=$env:V +} + +if ($null -ne $env:E) { + $env:GGML_HEXAGON_EXPERIMENTAL=$env:E +} + +if ($null -ne $env:SCHED) { + $env:GGML_SCHED_DEBUG=$env:SCHED; $cli_opts="$cli_opts -v" +} + +if ($null -ne $env:PROF) { + $env:GGML_HEXAGON_PROFILE=$env:PROF; $env:GGML_HEXAGON_OPSYNC=1 +} + +if ($null -ne $env:OPMASK) { + $env:GGML_HEXAGON_OPMASK=$env:OPMASK +} + +if ($null -ne $env:NHVX) { + $env:GGML_HEXAGON_NHVX=$env:NHVX +} + +if ($null -ne $env:NDEV) { + $env:GGML_HEXAGON_NDEV=$env:NDEV +} + +$env:ADSP_LIBRARY_PATH="$basedir\lib" + +& "$basedir\bin\llama-completion.exe" ` + --no-mmap -m $basedir\..\..\gguf\$model ` + --poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1 ` + --ctx-size 8192 --batch-size 128 -fa on ` + -ngl 99 -no-cnv --device $device $cli_opts