From 272acb4c7fd9f7130697c62809907581b36aa9cf Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Mon, 5 Oct 2026 23:56:36 -0700
Subject: [PATCH] frank-primary: two stacking fixes from the first live run

- release the numpy frombuffer view before closing the source mmap
  (Python 3.14 BufferError: cannot close exported pointers exist).
- stacked scale planes rename: checkpoint.cpp scale_name() appends
  _scale_inv to the STACKED tensor name verbatim (no .weight segment) -
  ...experts.gate_up_proj_scale_inv, not ...gate_up_proj.weight_scale_inv.
---
 scripts/stack-qwen38-official-fp8.py | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/scripts/stack-qwen38-official-fp8.py b/scripts/stack-qwen38-official-fp8.py
index 132c77a..c5db5d2 100755
--- a/scripts/stack-qwen38-official-fp8.py
+++ b/scripts/stack-qwen38-official-fp8.py
@@ -7,9 +7,11 @@ leaves the box). Two transforms, both VALUE-PRESERVING:
 
 1. EXPERTS: the shipped plugin's stacked layout names ONE tensor per family
    (`mlp.experts.gate_up_proj` [E, 2F, H], `mlp.experts.down_proj` [E, H, F])
-   plus a `_scale_inv` plane at the same index, while the official FP8 repo
-   ships per-expert unfused tensors (`experts.<e>.{gate,up,down}_proj.weight`
-   + scale). Stacking is pure byte concatenation along dim 0 — gate rows
+   plus a `<family>_scale_inv` plane at the same index (NO `.weight` in the
+   stacked name — scale_name() appends _scale_inv to the tensor name verbatim),
+   while the official FP8 repo ships per-expert unfused tensors
+   (`experts.<e>.{gate,up,down}_proj.weight` + scale). Stacking is pure byte
+   concatenation along dim 0 — gate rows
    first inside each expert's gate_up slab, which is the order the block
    wants (rad_block_moe_fp8.h: "a stacked gate_up is ALREADY FUSED in the
    order this block wants"). No requantisation: bytes are moved, not decoded.
@@ -195,10 +197,10 @@ def stack_prefix(job):
     out = os.path.join(stage, f"stacked.{idx:03d}.safetensors")
     tensors = [
         (f"{pre}.mlp.experts.gate_up_proj", F8, [n_e, f2, h], n_e * f2 * h),
-        (f"{pre}.mlp.experts.gate_up_proj.weight_scale_inv", BF16,
+        (f"{pre}.mlp.experts.gate_up_proj_scale_inv", BF16,
          [n_e, gs[0] * 2, gs[1]], n_e * gus_bytes),
         (f"{pre}.mlp.experts.down_proj", F8, [n_e, h, f], n_e * h * f),
-        (f"{pre}.mlp.experts.down_proj.weight_scale_inv", BF16,
+        (f"{pre}.mlp.experts.down_proj_scale_inv", BF16,
          [n_e, ds[0], ds[1]], n_e * ds_bytes),
     ]
     bufs = iter([gu, gus, dn, dns])
@@ -410,9 +412,9 @@ def main():
     for idx, pre in enumerate(prefixes):
         fname = f"stacked.{idx:03d}.safetensors"
         for t in (f"{pre}.mlp.experts.gate_up_proj",
-                  f"{pre}.mlp.experts.gate_up_proj.weight_scale_inv",
+                  f"{pre}.mlp.experts.gate_up_proj_scale_inv",
                   f"{pre}.mlp.experts.down_proj",
-                  f"{pre}.mlp.experts.down_proj.weight_scale_inv"):
+                  f"{pre}.mlp.experts.down_proj_scale_inv"):
             new_wm[t] = fname
     new_wm[merged_name] = out_name
     total = sum(meta_size(meta, k) for k in new_wm
@@ -500,10 +502,10 @@ def verify(stage, prefixes, n_e, shapes, meta, shard_ids, rows, hd,
         hlen2, hdr = parse_header(path)
         want = {
             f"{pre}.mlp.experts.gate_up_proj": (F8, [n_e, f2, h]),
-            f"{pre}.mlp.experts.gate_up_proj.weight_scale_inv":
+            f"{pre}.mlp.experts.gate_up_proj_scale_inv":
                 (BF16, [n_e, gs[0] * 2, gs[1]]),
             f"{pre}.mlp.experts.down_proj": (F8, [n_e, h, f]),
-            f"{pre}.mlp.experts.down_proj.weight_scale_inv": (BF16, [n_e, ds[0], ds[1]]),
+            f"{pre}.mlp.experts.down_proj_scale_inv": (BF16, [n_e, ds[0], ds[1]]),
         }
         for name, (dt, shp) in want.items():
             e = hdr[name]