ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

studio: revert combined targets, keep separate builds

Browse source 
Restore separate cmake --build calls for llama-server and
llama-quantize on both setup.sh and setup.ps1. The combined
approach made llama-quantize failure fatal, but it was originally
best-effort (|| true on Linux, [WARN] on Windows). The timing
savings from combining was only ~2.7s, not worth the semantic
change.

The Ninja + arch detection speedups are preserved (55s vs 1m 37s).
This commit is contained in:
Daniel Han 2026-03-14 06:33:15 +00:00
commit 6dda8c4c23
2 changed files with 20 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

18
studio/setup.ps1
View file

@ -898,20 +898,30 @@ if (Test-Path $LlamaServerBin) {
}
}
# -- Step C: Build llama-server + llama-quantize --
# -- Step C: Build llama-server --
$NumCpu = [Environment]::ProcessorCount
if ($NumCpu -lt 1) { $NumCpu = 4 }
if ($BuildOk) {
Write-Host ""
Write-Host "--- cmake build (llama-server + llama-quantize) ---" -ForegroundColor Cyan
Write-Host "--- cmake build (llama-server) ---" -ForegroundColor Cyan
Write-Host " Parallel jobs: $NumCpu" -ForegroundColor Gray
Write-Host ""
cmake --build $BuildDir --config Release --target llama-server llama-quantize -j $NumCpu
cmake --build $BuildDir --config Release --target llama-server -j $NumCpu
if ($LASTEXITCODE -ne 0) {
$BuildOk = $false
$FailedStep = "cmake build (llama-server + llama-quantize)"
$FailedStep = "cmake build (llama-server)"
}
}
# -- Step D: Build llama-quantize (optional, best-effort) --
if ($BuildOk) {
Write-Host ""
Write-Host "--- cmake build (llama-quantize) ---" -ForegroundColor Cyan
cmake --build $BuildDir --config Release --target llama-quantize -j $NumCpu
if ($LASTEXITCODE -ne 0) {
Write-Host " [WARN] llama-quantize build failed (GGUF export may be unavailable)" -ForegroundColor Yellow
}
}

8
studio/setup.sh
View file

@ -331,8 +331,12 @@ rm -rf "$LLAMA_CPP_DIR"
fi
if [ "$BUILD_OK" = true ]; then
# Build both targets in one invocation for better parallelism
run_quiet "build llama-server + llama-quantize" cmake --build "$LLAMA_CPP_DIR/build" --config Release --target llama-server llama-quantize -j"$NCPU" || BUILD_OK=false
run_quiet "build llama-server" cmake --build "$LLAMA_CPP_DIR/build" --config Release --target llama-server -j"$NCPU" || BUILD_OK=false
fi
# Also build llama-quantize (needed by unsloth-zoo's GGUF export pipeline)
if [ "$BUILD_OK" = true ]; then
run_quiet "build llama-quantize" cmake --build "$LLAMA_CPP_DIR/build" --config Release --target llama-quantize -j"$NCPU" || true
# Symlink to llama.cpp root — check_llama_cpp() looks for the binary there
QUANTIZE_BIN="$LLAMA_CPP_DIR/build/bin/llama-quantize"
if [ -f "$QUANTIZE_BIN" ]; then