align platform build config with working submission

computility-run.yaml

@@ -8,7 +8,7 @@ command:
     - --served-model-name
     - llm
     - --max-model-len
-    - '100000'
+    - '245000'
     - --gpu-memory-utilization
     - '0.9'
     - --trust-remote-code
@@ -19,16 +19,34 @@ command:
     - --disable-log-requests
     - --disable-frontend-multiprocessing
     - --max-num-batched-tokens
-    - '8192'
+    - '16384'
     - --enable-chunked-prefill
     - --max-seq-len-to-capture
-    - '32768'
+    - '245000'
     - --enable-auto-tool-choice
     - --tool-call-parser
     - qwen3_coder
     - --reasoning-parser
     - qwen3
     - --enable-prefix-caching
+    - --chat-template
+    - /workspace/chat_template_multi_system.jinja
 env:
     - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
       value: 3600
+    - name: PYTHONPATH
+      value: /usr/local/corex/lib64/python3/dist-packages
+    - name: LD_LIBRARY_PATH
+      value: /usr/local/corex/lib64:/usr/local/iluvatar/lib64:/usr/local/openmpi/lib
+    - name: PATH
+      value: /usr/local/corex/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/openmpi/bin
+    - name: MOE_NATIVE
+      value: '1'
+    - name: CHUNK_PARALLEL
+      value: '1'
+    - name: PREFIX_FLASH
+      value: '1'
+    - name: RMSNORM_NATIVE
+      value: '1'
+    - name: LOOP1_NATIVE
+      value: '1'