From 2680d62ec8b5951b42f303f3fa34ba31e1729e15 Mon Sep 17 00:00:00 2001
From: project6 <dev@project6.ai>
Date: Fri, 7 Aug 2026 10:27:53 +0000
Subject: [PATCH] fix(critical): match Sub168 config exactly + disable risky
 numerical patch

1. computility-run.yaml: restore Sub168's proven params:
   - max-model-len=256000 (not 100000)
   - gpu-memory-utilization=0.95 (not 0.90)
   - max-num-seqs=2 (not 1)
   - max-num-batched-tokens=4096 (restored)
   - enable-chunked-prefill (restored)
   These params worked for Sub168. Now that pip install is removed,
   they should work for us too.

2. patch_ops.sh: disable patch_numerical_stability.py
   If corex_gdn loads (which it should without pip install breaking deps),
   Python GatedDeltaNet fallback never runs, so numerical patches are
   unnecessary. Running regex replacements on qwen3_5.py risks breaking
   corex import conditions.
---
 computility-run.yaml         |  9 ++++++---
 qwen3_6_scripts/patch_ops.sh | 20 ++++++++------------
 2 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/computility-run.yaml b/computility-run.yaml
index 6c0d5cb1..0be4999a 100644
--- a/computility-run.yaml
+++ b/computility-run.yaml
@@ -8,14 +8,16 @@ command:
     - --served-model-name
     - llm
     - --max-model-len
-    - '100000'
+    - '256000'
     - --gpu-memory-utilization
-    - '0.90'
+    - '0.95'
     - --trust-remote-code
     - -tp
     - '4'
     - --max-num-seqs
-    - '1'
+    - '2'
+    - --max-num-batched-tokens
+    - '4096'
     - --disable-log-requests
     - --disable-frontend-multiprocessing
     - --enforce-eager
@@ -25,6 +27,7 @@ command:
     - --reasoning-parser
     - qwen3
     - --enable-prefix-caching
+    - --enable-chunked-prefill
     - --dtype
     - half
 env:
diff --git a/qwen3_6_scripts/patch_ops.sh b/qwen3_6_scripts/patch_ops.sh
index 4b0e40c7..c3ea5457 100755
--- a/qwen3_6_scripts/patch_ops.sh
+++ b/qwen3_6_scripts/patch_ops.sh
@@ -107,19 +107,15 @@ done
 echo "[patch_ops] reasoning parser + serving files installed"
 
 # ============================================================
-# 4. CCCL Agent-pattern: numerical stability patch for qwen3_5.py
-#    Sub509 docker logs: 99.98% NaN in every GatedDeltaNet layer.
-#    Base image has NaN detection + nan_to_num(nan=0.0), but that
-#    means DeltaNet layers output all-zeros → model "brain dead"
-#    → can't produce <tool_call> XML → d03 FAIL.
-#
-#    Strategy (CCCL optionally_static): detect what guards exist,
-#    inject ONLY what's missing. Preserve corex kernel paths.
-#    Agent flow: Init → Detect → Patch → Verify.
+# 4. Numerical stability patch — DISABLED
+#    If corex_gdn loads (which it should without pip install),
+#    the Python _torch_chunk_gated_delta_rule is NEVER called.
+#    Patching qwen3_5.py risks breaking corex import conditions.
+#    Only enable this if docker logs still show NaN after corex fix.
 # ============================================================
-python3 ./patch_numerical_stability.py 2>&1 || \
-    echo "[patch_ops] WARNING: numerical stability patch failed (non-fatal)"
-echo "[patch_ops] numerical stability patch complete"
+# python3 ./patch_numerical_stability.py 2>&1 || \
+#     echo "[patch_ops] WARNING: numerical stability patch failed (non-fatal)"
+echo "[patch_ops] numerical stability patch SKIPPED (corex_gdn handles DeltaNet)"
 
 # ============================================================
 # 5. DO NOT full-replace these files — base image has optimized versions.