ci(mlx): use llama-server /completion for GGUF inference test

Studio's install_llama_prebuilt.py only bundles llama-server +
llama-quantize from the prebuilt (line 3677:
return ["llama-server", "llama-quantize", "lib*.dylib"]); the
upstream tarball's llama-cli is intentionally dropped because
Studio drives inference through llama-server's HTTP API, not the
CLI. Switch the CI step to:

  1. Verify both binaries are present + dynamically link
     (llama-quantize --help is a cheap loader smoke test).
  2. Start llama-server with the downloaded
     unsloth/gemma-3-270m-it-GGUF Q4_K_M model on
     127.0.0.1:18080.
  3. Wait up to 30s for /health to come up.
  4. POST a /completion request with the same fixed
     temperature=0 / seed=3407 settings used elsewhere.
  5. Assert the response's `content` field is non-empty.

This drives the same install + inference path Studio's setup.sh
takes on macOS (which already passes --published-repo
ggml-org/llama.cpp + --simple-policy) and the same runtime path
Studio's chat backend takes (HTTP /completion against
llama-server).

.github/workflows/mlx-ci.yml

@@ -249,28 +249,30 @@ jobs:
           # at upstream ggml-org/llama.cpp; that repo doesn't ship the
           # llama-prebuilt-manifest.json asset Studio's default policy
           # expects, so the simple platform-specific policy maps
-          # Darwin+arm64 -> bin-macos-arm64 directly. setup.sh passes
-          # this flag too.
+          # Darwin+arm64 -> bin-macos-arm64 directly. studio/setup.sh
+          # passes both --published-repo ggml-org/llama.cpp AND
+          # --simple-policy automatically on macOS, so this CI step
+          # exercises the same code path users hit when they run
+          # `curl -fsSL https://unsloth.ai/install.sh | sh`.
           python studio/install_llama_prebuilt.py \
             --install-dir "$INSTALL_DIR" \
             --published-repo ggml-org/llama.cpp \
             --published-release-tag b9049 \
             --simple-policy
 
-          LLAMA_CLI=""
-          for c in \
-            "$INSTALL_DIR/build/bin/llama-cli" \
-            "$INSTALL_DIR/llama-cli" \
-            "$INSTALL_DIR/bin/llama-cli"; do
-            if [ -x "$c" ]; then LLAMA_CLI="$c"; break; fi
-          done
-          if [ -z "$LLAMA_CLI" ]; then
-            echo "::error::llama-cli not found under $INSTALL_DIR"
-            find "$INSTALL_DIR" -maxdepth 4 -type f -name 'llama-*' || true
-            exit 1
-          fi
-          echo "found llama-cli at: $LLAMA_CLI"
-          "$LLAMA_CLI" --version || true
+          # Studio bundles only llama-server + llama-quantize from the
+          # prebuilt (not llama-cli) -- inference goes through
+          # llama-server's HTTP /completion endpoint. Validate both:
+          # llama-quantize --help proves the dynamic libs link, then
+          # spin up llama-server and POST a /completion request on a
+          # tiny published GGUF.
+          LLAMA_SERVER="$INSTALL_DIR/build/bin/llama-server"
+          LLAMA_QUANT="$INSTALL_DIR/build/bin/llama-quantize"
+          [ -x "$LLAMA_SERVER" ] || { echo "::error::llama-server missing at $LLAMA_SERVER"; find "$INSTALL_DIR/build" -type f | head -40; exit 1; }
+          [ -x "$LLAMA_QUANT" ]  || { echo "::error::llama-quantize missing at $LLAMA_QUANT"; exit 1; }
+          echo "llama-server : $LLAMA_SERVER"
+          echo "llama-quantize: $LLAMA_QUANT"
+          "$LLAMA_QUANT" --help >/dev/null && echo "  llama-quantize loads OK"
 
           mkdir -p /tmp/ggufs
           python -c "
@@ -283,26 +285,48 @@ jobs:
           print('downloaded:', p)
           "
 
-          PROMPT="Hello, my name is"
-          echo "=== llama-cli inference ==="
-          OUT=$("$LLAMA_CLI" \
+          PORT=18080
+          echo "=== starting llama-server on 127.0.0.1:$PORT ==="
+          "$LLAMA_SERVER" \
             -m /tmp/ggufs/gemma-3-270m-it-Q4_K_M.gguf \
-            -p "$PROMPT" \
+            --host 127.0.0.1 \
+            --port "$PORT" \
+            -c 256 \
             -n 16 \
-            --temp 0 \
-            --seed 3407 \
-            -no-cnv \
-            --no-warmup 2>&1) || {
-              echo "::error::llama-cli exited non-zero"
-              echo "$OUT" | head -80
-              exit 1
-            }
-          echo "$OUT" | tail -40
-          if ! echo "$OUT" | grep -q "Hello"; then
-            echo "::error::llama-cli output did not contain the prompt echo 'Hello'"
+            --no-warmup \
+            > /tmp/llama-server.log 2>&1 &
+          SERVER_PID=$!
+          trap 'kill "$SERVER_PID" 2>/dev/null || true' EXIT
+
+          # Wait for /health to come up
+          for i in $(seq 1 30); do
+            if curl -sf "http://127.0.0.1:$PORT/health" >/dev/null 2>&1; then
+              echo "  server up after ${i}s"
+              break
+            fi
+            sleep 1
+          done
+          if ! curl -sf "http://127.0.0.1:$PORT/health" >/dev/null 2>&1; then
+            echo "::error::llama-server never became healthy"
+            tail -40 /tmp/llama-server.log
             exit 1
           fi
-          echo "OK: Studio prebuilt llama.cpp on Mac M1 + GGUF inference works"
+
+          PROMPT="Hello, my name is"
+          echo "=== POST /completion ==="
+          RESP=$(curl -sf -X POST "http://127.0.0.1:$PORT/completion" \
+            -H 'Content-Type: application/json' \
+            -d "{\"prompt\":\"$PROMPT\",\"n_predict\":16,\"temperature\":0,\"seed\":3407}")
+          echo "raw response (head): $(echo "$RESP" | head -c 600)"
+          CONTENT=$(echo "$RESP" | python -c "import json,sys; print(json.loads(sys.stdin.read()).get('content',''))")
+          echo "completion content: $CONTENT"
+
+          if [ -z "$CONTENT" ]; then
+            echo "::error::llama-server /completion returned empty content"
+            tail -40 /tmp/llama-server.log
+            exit 1
+          fi
+          echo "OK: Studio prebuilt llama.cpp on Mac M1 + GGUF /completion works"
 
       # Real MLX training + inference smoke test. Trains
       # unsloth/gemma-3-270m-it for 7 deterministic LoRA steps