Merge branch 'ggml-org:master' into master

Author: Thireus

src/llama-model.cpp

@@ -4825,11 +4825,13 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
                         // NextN/MTP tensors (preserved but unused) - conditionally load for last nextn_predict_layers
                         if (hparams.nextn_predict_layers > 0 && static_cast<uint32_t>(i) >= n_layer - hparams.nextn_predict_layers) {
                             layer.nextn.eh_proj          = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", i), { 2 * n_embd, n_embd }, flags);
-                            layer.nextn.embed_tokens     = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS, "weight", i), { n_embd, n_vocab }, flags);
                             layer.nextn.enorm            = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", i), { n_embd }, flags);
                             layer.nextn.hnorm            = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", i), { n_embd }, flags);
-                            layer.nextn.shared_head_head = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "weight", i), { n_embd, n_vocab }, flags);
-                            layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", i), { n_embd }, flags);
+
+                            // Optional tensors
+                            layer.nextn.embed_tokens     = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS, "weight", i), { n_embd, n_vocab }, flags | TENSOR_NOT_REQUIRED);
+                            layer.nextn.shared_head_head = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "weight", i), { n_embd, n_vocab }, flags | TENSOR_NOT_REQUIRED);
+                            layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", i), { n_embd }, flags | TENSOR_NOT_REQUIRED);
                         }
                     }
                 }

tools/server/webui/scripts/dev.sh

@@ -1,5 +1,14 @@
 #!/bin/bash
 
+# Development script for llama.cpp webui
+# 
+# This script starts the webui development servers (Storybook and Vite).
+# Note: You need to start llama-server separately.
+#
+# Usage:
+#   bash scripts/dev.sh
+#   npm run dev
+
 cd ../../../
 
 # Check and install git hooks if missing
@@ -28,76 +37,19 @@ check_and_install_hooks() {
 # Install git hooks if needed
 check_and_install_hooks
 
-# Check if llama-server binary already exists
-if [ ! -f "build/bin/llama-server" ]; then
-    echo "Building llama-server..."
-    cmake -B build && cmake --build build --config Release -t llama-server
-else
-    echo "llama-server binary already exists, skipping build."
-fi
-
-# Start llama-server and capture output
-echo "Starting llama-server..."
-mkfifo server_output.pipe
-build/bin/llama-server -hf ggml-org/gpt-oss-20b-GGUF --jinja -c 0 --no-webui > server_output.pipe 2>&1 &
-SERVER_PID=$!
-
-# Function to wait for server to be ready
-wait_for_server() {
-    echo "Waiting for llama-server to be ready..."
-    local max_wait=60
-    local start_time=$(date +%s)
-    
-    # Read server output in background and look for the ready message
-    (
-        while IFS= read -r line; do
-            echo "🔍 Server: $line"
-            if [[ "$line" == *"server is listening on http://127.0.0.1:8080 - starting the main loop"* ]]; then
-                echo "✅ llama-server is ready!"
-                echo "READY" > server_ready.flag
-                break
-            fi
-        done < server_output.pipe
-    ) &
-    
-    # Wait for ready flag or timeout
-    while [ ! -f server_ready.flag ]; do
-        local current_time=$(date +%s)
-        local elapsed=$((current_time - start_time))
-        
-        if [ $elapsed -ge $max_wait ]; then
-            echo "❌ Server failed to start within $max_wait seconds"
-            rm -f server_ready.flag
-            return 1
-        fi
-        
-        sleep 1
-    done
-    
-    rm -f server_ready.flag
-    return 0
-}
-
 # Cleanup function
 cleanup() {
     echo "🧹 Cleaning up..."
-    kill $SERVER_PID 2>/dev/null
-    rm -f server_output.pipe server_ready.flag
     exit
 }
 
 # Set up signal handlers
 trap cleanup SIGINT SIGTERM
 
-# Wait for server to be ready
-if wait_for_server; then
-    echo "🚀 Starting development servers..."
-    cd tools/server/webui
-    storybook dev -p 6006 --ci & vite dev --host 0.0.0.0 &
-    
-    # Wait for all background processes
-    wait
-else
-    echo "❌ Failed to start development environment"
-    cleanup
-fi
+echo "🚀 Starting development servers..."
+echo "📝 Note: Make sure to start llama-server separately if needed"
+cd tools/server/webui
+storybook dev -p 6006 --ci & vite dev --host 0.0.0.0 &
+
+# Wait for all background processes
+wait