fix(CRITICAL): stop overwriting base image model layer — match comp 168 strategy

Root cause of ALL failures: we overwrite base image's production code with our
inferior versions, breaking multimodal, killing C++ kernel performance, and
causing engine death.

Comp 168 evidence (48/52 pass, score=60194):
  - Uses base image qwen3_5.py (81706B) with full multimodal + CoreX integration
  - Uses base image corex_gdn/moe/fa2.py with real C++ kernels (libcorex_gdn.so)
  - Uses base image _custom_ops.py (ERROR spam is harmless)
  - d01: 8.49s, d05 multimodal: PASS, t13 base64 image: PASS

Our sub 508 (21/52 pass, score=0):
  - Overwrites qwen3_5.py → NO multimodal → engine death on image request
  - Overwrites corex_*.py → Python fallback → d01: 95.87s (11x slower)
  - Overwrites _custom_ops.py → may break base fallback chain

Changes:
1. patch_ops.sh: qwen3_5.py — KEEP base if >1000 bytes (was: ALWAYS overwrite)
2. patch_ops.sh: corex_*.py — KEEP base if >500 bytes (was: ALWAYS overwrite)
3. patch_ops.sh: _custom_ops.py — KEEP base always (was: ALWAYS overwrite)
4. computility-run.yaml: match comp 168 exactly:
   - max_model_len: 80000 → 256000
   - gpu_memory_utilization: 0.95 → 0.9
   - max_num_seqs: 2 → 1
   - REMOVE chunked_prefill + batched_tokens
   - REMOVE limit-mm-per-prompt (base image handles it)

computility-run.yaml

@@ -8,17 +8,14 @@ command:
     - --served-model-name
     - llm
     - --max-model-len
-    - '80000'
+    - '256000'
     - --gpu-memory-utilization
-    - '0.95'
+    - '0.9'
     - --trust-remote-code
     - -tp
     - '4'
     - --max-num-seqs
-    - '2'
-    - --max-num-batched-tokens
-    - '4096'
-    - --enable-chunked-prefill
+    - '1'
     - --disable-log-requests
     - --disable-frontend-multiprocessing
     - --enforce-eager
@@ -32,8 +29,6 @@ command:
     - '8192'
     - --dtype
     - half
-    - --limit-mm-per-prompt
-    - image=5
 env:
     - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
       value: '3600'