feat: batch forward for prompt

[rain1201]

What does this PR do?

Add batch forward to process full prompt while reading the model for only one time.

Type of change

• Performance improvement

Testing

• Tested on x86-64 (Linux/macOS/Windows)
• Tested with TinyLlama 1.1B Q4_K_M

Test command:

./picolm model.gguf -p "The capital of France is" -n 20 -t 0

Output:

Loading model: ../../tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf
Model config:
  n_embd=2048, n_ffn=5632, n_heads=32, n_kv_heads=4
  n_layers=22, vocab_size=32000, max_seq=2048
  head_dim=64, rope_base=10000.0
Allocating 1.17 MB for runtime state (+ 44.00 MB FP16 KV cache)
Tokenizer loaded: 32000 tokens, bos=1, eos=2
Prompt: 6 tokens, generating up to 20 (temp=0.00, top_p=0.90, threads=4)
---
Paris.

2. B.C. The capital of ancient Rome was Rome.

3
---

Checklist

• Code compiles without warnings (make native)
• No new dependencies added
• Memory usage not increased (check stderr output)