fix(CRITICAL): REVERT to serving-only patches — Sub168 proves CoreX native model is correct

THE OTHER CLAUDE'S COMMIT (5b8d7c6) IS WRONG. IT DEPLOYS ALL CUSTOM FILES.

Docker log evidence proves this is the root cause of ALL our failures:

Sub168 (07-23, PASS all d-tests):
  corex_gdn.py:56  'Loaded fused CoreX GDN decode operator'
  corex_moe.py:339 'Using CoreX fused MoE prefill: expert-grouped-wmma'
  model_runner.py:1074 (BASE IMAGE native)
  weights: 17.3529 GB
  NaN: 0 times

Our Sub508 (08-07, 41.2%):
  NO corex_gdn loading
  model_runner.py:1119 (OUR CUSTOM — wrong)
  weights: 16.2303 GB (1.1GB MISSING)
  NaN: 16 times, FusedMoE fail: 19 times

Our custom qwen3_5.py REPLACES the base image's CoreX-accelerated model
with pure-PyTorch code that:
  - Produces 99.98% NaN in every GatedDeltaNet layer
  - Falls back to Python MoE loop (base image uses WMMA hardware)
  - Loses 1.1GB of weights (broken load_weights function)

THIS COMMIT: deploy ONLY serving layer, keep base image model intact.
computility-run.yaml: exact Sub168 params (256K, 0.95, seqs=2, chunked).

computility-run.yaml

@@ -8,14 +8,14 @@ command:
     - --served-model-name
     - llm
     - --max-model-len
-    - '100000'
+    - '256000'
     - --gpu-memory-utilization
-    - '0.9'
+    - '0.95'
     - --trust-remote-code
     - -tp
     - '4'
     - --max-num-seqs
-    - '1'
+    - '2'
     - --max-num-batched-tokens
     - '4096'
     - --disable-log-requests