Add .env.example, Makefile; fix fp8_scaled_mm quantization policy

- Use build_policy(checkpoint_path) for fp8_scaled_mm
- Add .env.example template
- Add Makefile with common targets (install, api, docs, clean, lint)

app/service.py

@@ -83,15 +83,9 @@ class LtxService:
                 fuse_rule=fp8_cast_fuse_rule,
             )
         if q == "fp8_scaled_mm":
-            from ltx_core.quantization.fp8_scaled_mm import (
-                FP8_SCALED_MM_MODULE_OPS,
-                fp8_scaled_mm_fuse_rule,
-            )
-            from ltx_core.quantization.policy import QuantizationPolicy
+            from ltx_core.quantization.fp8_scaled_mm import build_policy as fp8_build
 
-            return QuantizationPolicy(
-                module_ops=FP8_SCALED_MM_MODULE_OPS, fuse_rule=fp8_scaled_mm_fuse_rule
-            )
+            return fp8_build(settings.ltx_distilled_checkpoint)
         return None
 
     async def submit_job(