From b85fcf4d6f3787cd7e653f545cdda20078819b5f Mon Sep 17 00:00:00 2001
From: biondizzle <biondizzle@gmail.com>
Date: Mon, 1 Jun 2026 02:49:55 +0000
Subject: [PATCH] diag: print SE global scales for first 3 layers

---
 single_shot_inference.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/single_shot_inference.py b/single_shot_inference.py
index 9c011392..2d68dbf3 100644
--- a/single_shot_inference.py
+++ b/single_shot_inference.py
@@ -422,6 +422,7 @@ def moe_forward(x, li, moe_runner, se_runner, router, token_id):
     shared_out = se_runner.run(x)
     if li < 3:
         print(f"  L{li} MoE shared: |out|={shared_out.abs().max().item():.4f} has_nan={torch.isnan(shared_out).any().item()}", flush=True)
+        print(f"  L{li} SE gsa: l1={se_runner._l1_activation_global_scale:.6f} l2={se_runner._l2_activation_global_scale:.6f} gsb: l1={se_runner._l1_gsb[0].item():.6f} l2={se_runner._l2_gsb[0].item():.6f}", flush=True)
     return routed_out + shared_out
 
 # =====================================================================