Tighten fault-path comments added by the video/diffusion hardening pass

scripts/fp8_layer_ablation.py

@@ -452,9 +452,8 @@ def main(argv = None) -> int:
     )
     t0 = time.perf_counter()
     pipe = _build_pipe(repo, force_fp32)
-    # _build_pipe returns a CPU pipeline (the bench applies levers first, then places on CUDA).
-    # The ablation captures a forward directly with a CUDA generator and reads the DiT off the
-    # GPU below, so place the pipeline on CUDA here rather than crashing on a cpu/cuda mismatch.
+    # _build_pipe returns a CPU pipeline; the ablation captures a forward with a CUDA generator,
+    # so place it on CUDA here to avoid a cpu/cuda mismatch.
     pipe = pipe.to("cuda")
     print(f"[load] pipe built in {time.perf_counter()-t0:.1f}s", flush = True)
 

scripts/sdpa_mask_backend_probe.py

@@ -30,8 +30,7 @@ def timed(fn, iters = 20):
         torch.cuda.synchronize()
         return (time.perf_counter() - t0) / iters * 1e3
     except torch.OutOfMemoryError:
-        # An occupied / too-small cuda:0 OOMs on the dense NxN mask; that is a memory limit,
-        # not a backend rejecting the mask, so don't mislabel it UNSUPPORTED.
+        # OOM on the dense NxN mask is a memory limit, not a backend rejecting it; don't mislabel UNSUPPORTED.
         torch.cuda.empty_cache()
         return "OOM"
     except Exception as e:  # noqa: BLE001

scripts/video_speedmem_bench.py

@@ -623,8 +623,8 @@ def _timed_video(
             marker = getattr(transformer, "_unsloth_step_cache", None)
             if not marker or str(marker).endswith(f"#s{int(steps)}"):
                 return "magcache"  # already sized for these steps
-            # Fail closed like production: reapplying over a cache that would not disengage
-            # double-hooks the transformer and times a stale/stacked curve as if it were fresh.
+            # Fail closed: reapplying over a cache that would not disengage double-hooks the
+            # transformer and times a stale curve as if it were fresh.
             if not _disengage_step_cache(
                 transformer,
                 reason = f"explicit magcache re-interpolating for {steps} steps",