scripts: skip macOS symlink creation if already correct

Dockerfile

@@ -147,7 +147,7 @@ ARG PARALLEL
 WORKDIR /go/src/github.com/ollama/ollama
 COPY CMakeLists.txt CMakePresets.json .
 COPY ml/backend/ggml/ggml ml/backend/ggml/ggml
-COPY x/ml/backend/mlx x/ml/backend/mlx
+COPY x/imagegen/mlx x/imagegen/mlx
 COPY go.mod go.sum .
 COPY MLX_VERSION .
 RUN curl -fsSL https://golang.org/dl/go$(awk '/^go/ { print $2 }' go.mod).linux-$(case $(uname -m) in x86_64) echo amd64 ;; aarch64) echo arm64 ;; esac).tar.gz | tar xz -C /usr/local

anthropic/anthropic.go

@@ -897,11 +897,5 @@ func countContentBlock(block any) int {
 		}
 	}
 
-	if source, ok := blockMap["source"].(map[string]any); ok {
-		if data, ok := source["data"].(string); ok {
-			total += len(data)
-		}
-	}
-
 	return total
 }

docs/faq.mdx

@@ -312,7 +312,7 @@ Parallel request processing for a given model results in increasing the context
 The following server settings may be used to adjust how Ollama handles concurrent requests on most platforms:
 
 - `OLLAMA_MAX_LOADED_MODELS` - The maximum number of models that can be loaded concurrently provided they fit in available memory. The default is 3 \* the number of GPUs or 3 for CPU inference.
-- `OLLAMA_NUM_PARALLEL` - The maximum number of parallel requests each model will process at the same time. The default will auto-select either 4 or 1 based on available memory.
+- `OLLAMA_NUM_PARALLEL` - The maximum number of parallel requests each model will process at the same time, default 1.  Required RAM will scale by `OLLAMA_NUM_PARALLEL` * `OLLAMA_CONTEXT_LENGTH`.
 - `OLLAMA_MAX_QUEUE` - The maximum number of requests Ollama will queue when busy before rejecting additional requests. The default is 512
 
 Note: Windows with Radeon GPUs currently default to 1 model maximum due to limitations in ROCm v5.7 for available VRAM reporting. Once ROCm v6.2 is available, Windows Radeon will follow the defaults above. You may enable concurrent model loads on Radeon on Windows, but ensure you don't load more models than will fit into your GPUs VRAM.

scripts/install.sh

@@ -49,11 +49,7 @@ if [ "$OS" = "Darwin" ]; then
         exit 1
     fi
 
-    if [ -n "${OLLAMA_VERSION:-}" ]; then
-        DOWNLOAD_URL="https://github.com/ollama/ollama/releases/download/${OLLAMA_VERSION}/Ollama-darwin.zip"
-    else
-        DOWNLOAD_URL="https://github.com/ollama/ollama/releases/latest/download/Ollama-darwin.zip"
-    fi
+    DOWNLOAD_URL="https://ollama.com/download/Ollama-darwin.zip${OLLAMA_VERSION:+?version=$OLLAMA_VERSION}"
 
     if pgrep -x Ollama >/dev/null 2>&1; then
         status "Stopping running Ollama instance..."
@@ -74,10 +70,12 @@ if [ "$OS" = "Darwin" ]; then
     unzip -q "$TEMP_DIR/Ollama-darwin.zip" -d "$TEMP_DIR"
     mv "$TEMP_DIR/Ollama.app" "/Applications/"
 
-    status "Adding 'ollama' command to PATH (may require password)..."
-    mkdir -p "/usr/local/bin" 2>/dev/null || sudo mkdir -p "/usr/local/bin"
-    ln -sf "/Applications/Ollama.app/Contents/Resources/ollama" "/usr/local/bin/ollama" 2>/dev/null || \
-        sudo ln -sf "/Applications/Ollama.app/Contents/Resources/ollama" "/usr/local/bin/ollama"
+    if [ ! -L "/usr/local/bin/ollama" ] || [ "$(readlink "/usr/local/bin/ollama")" != "/Applications/Ollama.app/Contents/Resources/ollama" ]; then
+        status "Adding 'ollama' command to PATH (may require password)..."
+        mkdir -p "/usr/local/bin" 2>/dev/null || sudo mkdir -p "/usr/local/bin"
+        ln -sf "/Applications/Ollama.app/Contents/Resources/ollama" "/usr/local/bin/ollama" 2>/dev/null || \
+            sudo ln -sf "/Applications/Ollama.app/Contents/Resources/ollama" "/usr/local/bin/ollama"
+    fi
 
     if [ -z "${OLLAMA_NO_START:-}" ]; then
         status "Starting Ollama..."