From 6dda8c4c233ce49e9d0d1be18c513ef103e60737 Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Sat, 14 Mar 2026 06:33:15 +0000
Subject: [PATCH] studio: revert combined targets, keep separate builds

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).
---
 studio/setup.ps1 | 18 ++++++++++++++----
 studio/setup.sh  |  8 ++++++--
 2 files changed, 20 insertions(+), 6 deletions(-)

diff --git a/studio/setup.ps1 b/studio/setup.ps1
index 7a15a893af..bf0ba754f0 100644
--- a/studio/setup.ps1
+++ b/studio/setup.ps1
@@ -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
         }
     }
 
diff --git a/studio/setup.sh b/studio/setup.sh
index 88576776c2..5cabb461c8 100755
--- a/studio/setup.sh
+++ b/studio/setup.sh
@@ -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