torch.compile + Inductor: Reduce-Overhead + Dynamic Shapes + Recompile Watcher

# === torch.compile training entegrasyonu ===
import torch
from transformers import AutoModelForCausalLM
 
model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Meta-Llama-3.1-8B-Instruct",
    torch_dtype="bfloat16",
    attn_implementation="flash_attention_2",
).cuda()
 
# Compile model
# mode options:
#   "default" — safe, balanced
#   "reduce-overhead" — CUDA graphs, en hızlı stable shapes için
#   "max-autotune" — agresif autotune, ilk warmup uzun
model = torch.compile(
    model,
    mode="reduce-overhead",
    fullgraph=False,                          # False — partial graph (safer)
    dynamic=True,                              # Variable shapes (seq length)
)
 
# Training loop unchanged
for batch in loader:
    loss = model(**batch).loss
    loss.backward()
    ...
 
# Bench:
# Vanilla:                  1.78 step/s
# + torch.compile default:  1.92 step/s (+%8)
# + reduce-overhead:        2.04 step/s (+%15)