Add timing instrumentation and user progress messages for model loading

Problem: Model loading takes 2-3 minutes on first load with no user feedback,
causing confusion about whether the system is frozen or working.

Root Cause: GPU initialization (reserveWorstCaseGraph) takes ~164 seconds on
Tesla K80 GPUs due to CUDA kernel compilation (PTX JIT for compute 3.7). This
is by design - it validates GPU compatibility before committing to full load.

Solution:
1. Add comprehensive timing instrumentation to identify bottlenecks
2. Add user-facing progress messages explaining the delay

Changes:
- cmd/cmd.go: Update spinner with informative message for users
- llama/llama.go: Add timing logs for CGO model loading
- runner/llamarunner/runner.go: Add detailed timing for llama runner
- runner/ollamarunner/runner.go: Add timing + stderr messages for new engine
- server/sched.go: Add timing for scheduler load operation

User Experience:
Before: Silent wait with blinking cursor for 2-3 minutes
After: Rotating spinner with message "loading model (may take 1-3 min on first load)"

Performance Metrics Captured:
- GGUF file reading: ~0.4s
- GPU kernel compilation: ~164s (bottleneck identified)
- Model weight loading: ~0.002s
- Total end-to-end: ~165s

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

server/sched.go

@@ -480,7 +480,10 @@ func (s *Scheduler) load(req *LlmRequest, f *ggml.GGML, systemInfo ml.SystemInfo
 	// Returns:
 	// - gpuIDs: List of GPU device IDs where model layers were loaded
 	// - err: Error if model doesn't fit or loading fails
+	slog.Info("scheduler.load: calling llama.Load() to load model into memory")
+	loadStart := time.Now()
 	gpuIDs, err := llama.Load(req.ctx, systemInfo, gpus, requireFull)
+	slog.Info("scheduler.load: llama.Load() completed", "duration_sec", time.Since(loadStart).Seconds(), "error", err)
 	if err != nil {
 		if errors.Is(err, llm.ErrLoadRequiredFull) {
 			if !requireFull {