Pass temperature and alpha to MTP speculative decoding

Default temp=0.7 (matching exo's default) so probabilistic acceptance
runs correctly. Configurable via EXO_SPECULATIVE_TEMP and
EXO_SPECULATIVE_ALPHA env vars.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: davidmcc73

src/exo/worker/engines/mlx/generator/batch_generate.py

@@ -93,10 +93,14 @@ def __post_init__(self) -> None:
 
                 if mtp_weights and os.path.exists(mtp_weights):
                     mtp = MTPPredictor(self.model, mtp_weights, quantize=False)
+                    temp = float(os.environ.get("EXO_SPECULATIVE_TEMP", "0.7"))
+                    alpha = float(os.environ.get("EXO_SPECULATIVE_ALPHA", "1.0"))
                     self._exo_gen = MTPBatchGenerator(
                         model=self.model,
                         mtp_predictor=mtp,
                         gamma=gamma,
+                        temp=temp,
+                        alpha=alpha,
                         stop_tokens=stop_tokens,
                         prefill_step_size=4096,
                     )