revert: restore a3c45d3b yaml + Q-tiling + remove all OOM hacks

Root cause of 10 consecutive OOM failures:
- 'return zeros during profiling' hack → vllm overestimates free memory
  → allocates 7942 blocks → first real request OOMs
- blocks cap 5000 → band-aid that masks profiling bug
- gpu-memory-utilization 0.80 → unnecessary reduction from working 0.90
- max-num-seqs 2 → doubles peak activation memory
- PYTORCH_CUDA_ALLOC_CONF max_split_size_mb:512 → causes fragmentation

Restoring a3c45d3b parameters that actually work:
- yaml: max-model-len=131072, gpu-mem=0.90, max-num-seqs=1, batched-tokens=8192
- patch_xformers_sdpa_seq.py: Q-tiling (real memory optimization, not zeros hack)
- patch_block_major_worker_capacity.py: no blocks cap, just reserve_block_major
- patch_ops.sh: remove all docker-build-time compilation (all .so are prebuilt)

Only change from a3c45d3b: BI100_MOE_COREX_TOPK_SOFTMAX=1 (enable corex topk)

Kept fixes:
- protocol.py extra=allow (recover 180 rejected replay requests)
- corex_gdn_chunk_recurrent.so pybind kwargs (prebuilt with fixed signature)

computility-run.yaml

@@ -8,18 +8,18 @@ command:
     - --served-model-name
     - llm
     - --max-model-len
-    - '80000'
+    - '131072'
     - --gpu-memory-utilization
-    - '0.80'
+    - '0.90'
     - --trust-remote-code
     - -tp
     - '4'
     - --max-num-seqs
-    - '2'
+    - '1'
     - --disable-log-requests
     - --disable-frontend-multiprocessing
     - --max-num-batched-tokens
-    - '4096'
+    - '8192'
     - --enable-chunked-prefill
     - --max-seq-len-to-capture
     - '32768'
@@ -47,5 +47,3 @@ env:
       value: hybrid64
     - name: BI100_MOE_COREX_TOPK_SOFTMAX
       value: '1'
-    - name: PYTORCH_CUDA_ALLOC_CONF
-      value: max_split_size_mb:512