mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-03-06 23:30:06 +01:00
ce38a4db47
* hexagon: updates to enable offloading to HTP on WoS * Update windows.md * Update windows.md * hexagon: enable -O3 optimizations * hexagon: move all _WINDOWS conditional compilation to _WIN32 * hexagon: updates to enable offloading to HTP on WoS * hexagon: use run-time vs load-time dynamic linking for cdsp driver interface * refactor htp-drv * hexagon: add run-bench.ps1 script * hexagon: htdrv refactor * hexagon: unify Android and Windows build readmes * hexagon: update README.md * hexagon: refactor htpdrv * hexagon: drv refactor * hexagon: more drv refactor * hexagon: fixes for android builds * hexagon: factor out dl into ggml-backend-dl * hexagon: add run-tool.ps1 script * hexagon: merge htp-utils in htp-drv and remove unused code * wos: no need for getopt_custom.h * wos: add missing CR in htpdrv * hexagon: ndev enforecement applies only to the Android devices * hexagon: add support for generating and signing .cat file * hexagon: add .inf file * hexagon: working auto-signing and improved windows builds * hexagon: futher improve skel build * hexagon: add rough WoS guide * hexagon: updated windows guide * hexagon: improve cmake handling of certs and logging * hexagon: improve windows setup/build doc * hexagon: more windows readme updates * hexagon: windows readme updates * hexagon: windows readme updates * hexagon: windows readme updates * hexagon: windows readme updates * Update windows.md * Update windows.md * snapdragon: rename docs/backend/hexagon to docs/backends/snapdragon Also added a power shell script to simplify build env setup. * hexagon: remove trailing whitespace and move cmake requirement to user-presets * hexagon: fix CMakeUserPresets path in workflow yaml * hexagon: introduce local version of libdl.h * hexagon: fix src1 reuse logic gpt-oss needs a bigger lookahead window. The check for src[1] itself being quantized was wrong. --------- Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>
54 lines
1.0 KiB
PowerShell
54 lines
1.0 KiB
PowerShell
|
|
#!/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 -no-cnv -m $basedir\..\..\gguf\$model `
|
|
--poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1 `
|
|
--ctx-size 8192 --batch-size 128 -ctk q8_0 -ctv q8_0 -fa on `
|
|
-ngl 99 --device $device $cli_opts
|